Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,127 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+env/bin/python filter=lfs diff=lfs merge=lfs -text
+env/bin/python3 filter=lfs diff=lfs merge=lfs -text
+env/bin/python3.12 filter=lfs diff=lfs merge=lfs -text
+env/bin/ruff filter=lfs diff=lfs merge=lfs -text
+env/lib/python3.12/site-packages/PIL/_imaging.cpython-312-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text
+env/lib/python3.12/site-packages/_cffi_backend.cpython-312-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text
+env/lib/python3.12/site-packages/_soundfile_data/libsndfile_x86_64.so filter=lfs diff=lfs merge=lfs -text
+env/lib/python3.12/site-packages/aiohttp/_http_parser.cpython-312-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text
+env/lib/python3.12/site-packages/bitsandbytes/libbitsandbytes_cuda117.so filter=lfs diff=lfs merge=lfs -text
+env/lib/python3.12/site-packages/bitsandbytes/libbitsandbytes_cuda117_nocublaslt.so filter=lfs diff=lfs merge=lfs -text
+env/lib/python3.12/site-packages/bitsandbytes/libbitsandbytes_cuda118.so filter=lfs diff=lfs merge=lfs -text
+env/lib/python3.12/site-packages/bitsandbytes/libbitsandbytes_cuda118_nocublaslt.so filter=lfs diff=lfs merge=lfs -text
+env/lib/python3.12/site-packages/bitsandbytes/libbitsandbytes_cuda120.so filter=lfs diff=lfs merge=lfs -text
+env/lib/python3.12/site-packages/bitsandbytes/libbitsandbytes_cuda120_nocublaslt.so filter=lfs diff=lfs merge=lfs -text
+env/lib/python3.12/site-packages/bitsandbytes/libbitsandbytes_cuda121.so filter=lfs diff=lfs merge=lfs -text
+env/lib/python3.12/site-packages/bitsandbytes/libbitsandbytes_cuda121_nocublaslt.so filter=lfs diff=lfs merge=lfs -text
+env/lib/python3.12/site-packages/bitsandbytes/libbitsandbytes_cuda122.so filter=lfs diff=lfs merge=lfs -text
+env/lib/python3.12/site-packages/bitsandbytes/libbitsandbytes_cuda122_nocublaslt.so filter=lfs diff=lfs merge=lfs -text
+env/lib/python3.12/site-packages/bitsandbytes/libbitsandbytes_cuda123.so filter=lfs diff=lfs merge=lfs -text
+env/lib/python3.12/site-packages/bitsandbytes/libbitsandbytes_cuda123_nocublaslt.so filter=lfs diff=lfs merge=lfs -text
+env/lib/python3.12/site-packages/bitsandbytes/libbitsandbytes_cuda124.so filter=lfs diff=lfs merge=lfs -text
+env/lib/python3.12/site-packages/bitsandbytes/libbitsandbytes_cuda124_nocublaslt.so filter=lfs diff=lfs merge=lfs -text
+env/lib/python3.12/site-packages/bitsandbytes/libbitsandbytes_cuda125.so filter=lfs diff=lfs merge=lfs -text
+env/lib/python3.12/site-packages/bitsandbytes/libbitsandbytes_cuda125_nocublaslt.so filter=lfs diff=lfs merge=lfs -text
+env/lib/python3.12/site-packages/fontTools/cu2qu/cu2qu.cpython-312-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text
+env/lib/python3.12/site-packages/fontTools/feaLib/lexer.cpython-312-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text
+env/lib/python3.12/site-packages/fontTools/misc/bezierTools.cpython-312-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text
+env/lib/python3.12/site-packages/fontTools/pens/momentsPen.cpython-312-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text
+env/lib/python3.12/site-packages/fontTools/qu2cu/qu2cu.cpython-312-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text
+env/lib/python3.12/site-packages/fontTools/varLib/iup.cpython-312-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text
+env/lib/python3.12/site-packages/gradio/_frontend_code/component-test/src/lib/images/world.mp4 filter=lfs diff=lfs merge=lfs -text
+env/lib/python3.12/site-packages/gradio/_frontend_code/spa/test/files/file_test.ogg filter=lfs diff=lfs merge=lfs -text
+env/lib/python3.12/site-packages/gradio/_frontend_code/spa/test/files/world.mp4 filter=lfs diff=lfs merge=lfs -text
+env/lib/python3.12/site-packages/gradio/frpc_linux_amd64_v0.2 filter=lfs diff=lfs merge=lfs -text
+env/lib/python3.12/site-packages/jieba/finalseg/__pycache__/prob_emit.cpython-312.pyc filter=lfs diff=lfs merge=lfs -text
+env/lib/python3.12/site-packages/jieba/lac_small/model_baseline/word_emb filter=lfs diff=lfs merge=lfs -text
+env/lib/python3.12/site-packages/jieba/posseg/__pycache__/prob_emit.cpython-312.pyc filter=lfs diff=lfs merge=lfs -text
+env/lib/python3.12/site-packages/kiwisolver/_cext.cpython-312-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text
+env/lib/python3.12/site-packages/llvmlite/binding/libllvmlite.so filter=lfs diff=lfs merge=lfs -text
+env/lib/python3.12/site-packages/msgpack/_cmsgpack.cpython-312-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text
+env/lib/python3.12/site-packages/numba/np/ufunc/tbbpool.cpython-312-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text
+env/lib/python3.12/site-packages/numpy/core/_multiarray_umath.cpython-312-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text
+env/lib/python3.12/site-packages/numpy/core/_simd.cpython-312-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text
+env/lib/python3.12/site-packages/numpy.libs/libgfortran-040039e1.so.5.0.0 filter=lfs diff=lfs merge=lfs -text
+env/lib/python3.12/site-packages/numpy.libs/libopenblas64_p-r0-0cf96a72.3.23.dev.so filter=lfs diff=lfs merge=lfs -text
+env/lib/python3.12/site-packages/nvidia/cublas/lib/libcublas.so.12 filter=lfs diff=lfs merge=lfs -text
+env/lib/python3.12/site-packages/nvidia/cublas/lib/libcublasLt.so.12 filter=lfs diff=lfs merge=lfs -text
+env/lib/python3.12/site-packages/nvidia/cuda_cupti/lib/libcheckpoint.so filter=lfs diff=lfs merge=lfs -text
+env/lib/python3.12/site-packages/nvidia/cuda_cupti/lib/libcupti.so.12 filter=lfs diff=lfs merge=lfs -text
+env/lib/python3.12/site-packages/nvidia/cuda_cupti/lib/libnvperf_host.so filter=lfs diff=lfs merge=lfs -text
+env/lib/python3.12/site-packages/nvidia/cuda_cupti/lib/libnvperf_target.so filter=lfs diff=lfs merge=lfs -text
+env/lib/python3.12/site-packages/nvidia/cuda_nvrtc/lib/libnvrtc-builtins.so.12.4 filter=lfs diff=lfs merge=lfs -text
+env/lib/python3.12/site-packages/nvidia/cuda_nvrtc/lib/libnvrtc.so.12 filter=lfs diff=lfs merge=lfs -text
+env/lib/python3.12/site-packages/nvidia/cudnn/lib/libcudnn_adv.so.9 filter=lfs diff=lfs merge=lfs -text
+env/lib/python3.12/site-packages/nvidia/cudnn/lib/libcudnn_cnn.so.9 filter=lfs diff=lfs merge=lfs -text
+env/lib/python3.12/site-packages/nvidia/cudnn/lib/libcudnn_engines_precompiled.so.9 filter=lfs diff=lfs merge=lfs -text
+env/lib/python3.12/site-packages/nvidia/cudnn/lib/libcudnn_engines_runtime_compiled.so.9 filter=lfs diff=lfs merge=lfs -text
+env/lib/python3.12/site-packages/nvidia/cudnn/lib/libcudnn_graph.so.9 filter=lfs diff=lfs merge=lfs -text
+env/lib/python3.12/site-packages/nvidia/cudnn/lib/libcudnn_heuristic.so.9 filter=lfs diff=lfs merge=lfs -text
+env/lib/python3.12/site-packages/nvidia/cudnn/lib/libcudnn_ops.so.9 filter=lfs diff=lfs merge=lfs -text
+env/lib/python3.12/site-packages/nvidia/cufft/lib/libcufft.so.11 filter=lfs diff=lfs merge=lfs -text
+env/lib/python3.12/site-packages/nvidia/curand/lib/libcurand.so.10 filter=lfs diff=lfs merge=lfs -text
+env/lib/python3.12/site-packages/nvidia/cusolver/lib/libcusolver.so.11 filter=lfs diff=lfs merge=lfs -text
+env/lib/python3.12/site-packages/nvidia/cusolver/lib/libcusolverMg.so.11 filter=lfs diff=lfs merge=lfs -text
+env/lib/python3.12/site-packages/nvidia/cusparse/lib/libcusparse.so.12 filter=lfs diff=lfs merge=lfs -text
+env/lib/python3.12/site-packages/nvidia/nccl/lib/libnccl.so.2 filter=lfs diff=lfs merge=lfs -text
+env/lib/python3.12/site-packages/nvidia/nvjitlink/lib/libnvJitLink.so.12 filter=lfs diff=lfs merge=lfs -text
+env/lib/python3.12/site-packages/pandas/_libs/algos.cpython-312-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text
+env/lib/python3.12/site-packages/pandas/_libs/groupby.cpython-312-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text
+env/lib/python3.12/site-packages/pandas/_libs/hashtable.cpython-312-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text
+env/lib/python3.12/site-packages/pandas/_libs/interval.cpython-312-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text
+env/lib/python3.12/site-packages/pandas/_libs/join.cpython-312-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text
+env/lib/python3.12/site-packages/pandas/_libs/tslibs/offsets.cpython-312-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text
+env/lib/python3.12/site-packages/pillow.libs/libfreetype-be14bf51.so.6.20.1 filter=lfs diff=lfs merge=lfs -text
+env/lib/python3.12/site-packages/pillow.libs/libharfbuzz-89381d8f.so.0.60850.0 filter=lfs diff=lfs merge=lfs -text
+env/lib/python3.12/site-packages/pyarrow/_compute.cpython-312-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text
+env/lib/python3.12/site-packages/pyarrow/_dataset.cpython-312-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text
+env/lib/python3.12/site-packages/pyarrow/_flight.cpython-312-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text
+env/lib/python3.12/site-packages/pyarrow/lib.cpython-312-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text
+env/lib/python3.12/site-packages/pyarrow/libarrow.so.1800 filter=lfs diff=lfs merge=lfs -text
+env/lib/python3.12/site-packages/pyarrow/libarrow_acero.so.1800 filter=lfs diff=lfs merge=lfs -text
+env/lib/python3.12/site-packages/pyarrow/libarrow_dataset.so.1800 filter=lfs diff=lfs merge=lfs -text
+env/lib/python3.12/site-packages/pyarrow/libarrow_flight.so.1800 filter=lfs diff=lfs merge=lfs -text
+env/lib/python3.12/site-packages/pyarrow/libarrow_python.so filter=lfs diff=lfs merge=lfs -text
+env/lib/python3.12/site-packages/pyarrow/libarrow_substrait.so.1800 filter=lfs diff=lfs merge=lfs -text
+env/lib/python3.12/site-packages/pyarrow/libparquet.so.1800 filter=lfs diff=lfs merge=lfs -text
+env/lib/python3.12/site-packages/pydantic_core/_pydantic_core.cpython-312-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text
+env/lib/python3.12/site-packages/regex/_regex.cpython-312-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text
+env/lib/python3.12/site-packages/safetensors/_safetensors_rust.cpython-312-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text
+env/lib/python3.12/site-packages/scipy/fft/_pocketfft/pypocketfft.cpython-312-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text
+env/lib/python3.12/site-packages/scipy/io/_fast_matrix_market/_fmm_core.cpython-312-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text
+env/lib/python3.12/site-packages/scipy/linalg/_fblas.cpython-312-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text
+env/lib/python3.12/site-packages/scipy/linalg/_flapack.cpython-312-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text
+env/lib/python3.12/site-packages/scipy/misc/face.dat filter=lfs diff=lfs merge=lfs -text
+env/lib/python3.12/site-packages/scipy/optimize/_highs/_highs_wrapper.cpython-312-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text
+env/lib/python3.12/site-packages/scipy/sparse/_sparsetools.cpython-312-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text
+env/lib/python3.12/site-packages/scipy/spatial/_qhull.cpython-312-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text
+env/lib/python3.12/site-packages/scipy/special/_ufuncs.cpython-312-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text
+env/lib/python3.12/site-packages/scipy/special/_ufuncs_cxx.cpython-312-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text
+env/lib/python3.12/site-packages/scipy/special/cython_special.cpython-312-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text
+env/lib/python3.12/site-packages/scipy/stats/_unuran/unuran_wrapper.cpython-312-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text
+env/lib/python3.12/site-packages/scipy.libs/libgfortran-040039e1-0352e75f.so.5.0.0 filter=lfs diff=lfs merge=lfs -text
+env/lib/python3.12/site-packages/scipy.libs/libgfortran-040039e1.so.5.0.0 filter=lfs diff=lfs merge=lfs -text
+env/lib/python3.12/site-packages/scipy.libs/libscipy_openblas-c128ec02.so filter=lfs diff=lfs merge=lfs -text
+env/lib/python3.12/site-packages/sklearn/_loss/_loss.cpython-312-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text
+env/lib/python3.12/site-packages/sympy/polys/benchmarks/__pycache__/bench_solvers.cpython-312.pyc filter=lfs diff=lfs merge=lfs -text
+env/lib/python3.12/site-packages/tokenizers/tokenizers.cpython-312-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text
+env/lib/python3.12/site-packages/torch/bin/protoc filter=lfs diff=lfs merge=lfs -text
+env/lib/python3.12/site-packages/torch/bin/protoc-3.13.0.0 filter=lfs diff=lfs merge=lfs -text
+env/lib/python3.12/site-packages/torch/lib/libc10.so filter=lfs diff=lfs merge=lfs -text
+env/lib/python3.12/site-packages/torch/lib/libcusparseLt-294d6944.so.0 filter=lfs diff=lfs merge=lfs -text
+env/lib/python3.12/site-packages/torch/lib/libtorch_cpu.so filter=lfs diff=lfs merge=lfs -text
+env/lib/python3.12/site-packages/torch/lib/libtorch_cuda.so filter=lfs diff=lfs merge=lfs -text
+env/lib/python3.12/site-packages/torch/lib/libtorch_cuda_linalg.so filter=lfs diff=lfs merge=lfs -text
+env/lib/python3.12/site-packages/torch/lib/libtorch_python.so filter=lfs diff=lfs merge=lfs -text
+env/lib/python3.12/site-packages/torchaudio/lib/libctc_prefix_decoder.so filter=lfs diff=lfs merge=lfs -text
+env/lib/python3.12/site-packages/torchaudio/lib/libtorchaudio.so filter=lfs diff=lfs merge=lfs -text
+env/lib/python3.12/site-packages/triton/_C/libproton.so filter=lfs diff=lfs merge=lfs -text
+env/lib/python3.12/site-packages/triton/_C/libtriton.so filter=lfs diff=lfs merge=lfs -text
+env/lib/python3.12/site-packages/triton/backends/nvidia/bin/nvdisasm filter=lfs diff=lfs merge=lfs -text
+env/lib/python3.12/site-packages/triton/backends/nvidia/bin/ptxas filter=lfs diff=lfs merge=lfs -text
+env/lib/python3.12/site-packages/wandb/bin/gpu_stats filter=lfs diff=lfs merge=lfs -text
+env/lib/python3.12/site-packages/wandb/bin/wandb-core filter=lfs diff=lfs merge=lfs -text
+env/lib/python3.12/site-packages/yaml/_yaml.cpython-312-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text

.github/ISSUE_TEMPLATE/bug_report.yml

@@ -0,0 +1,50 @@
+name: "Bug Report"
+description: |
+  Please provide as much details to help address the issue, including logs and screenshots.
+labels:
+  - bug
+body:
+  - type: checkboxes
+    attributes:
+      label: Checks
+      description: "To ensure timely help, please confirm the following:"
+      options:
+        - label: This template is only for bug reports, usage problems go with 'Help Wanted'.
+          required: true
+        - label: I have thoroughly reviewed the project documentation but couldn't find information to solve my problem.
+          required: true
+        - label: I have searched for existing issues, including closed ones, and couldn't find a solution.
+          required: true
+        - label: I confirm that I am using English to submit this report in order to facilitate communication.
+          required: true
+  - type: textarea
+    attributes:
+      label: Environment Details
+      description: "Provide details such as OS, Python version, and any relevant software or dependencies."
+      placeholder: e.g., CentOS Linux 7, RTX 3090, Python 3.10, torch==2.3.0, cuda 11.8
+    validations:
+      required: true
+  - type: textarea
+    attributes:
+      label: Steps to Reproduce
+      description: |
+        Include detailed steps, screenshots, and logs. Use the correct markdown syntax for code blocks.
+      placeholder: |
+        1. Create a new conda environment.
+        2. Clone the repository, install as local editable and properly set up.
+        3. Run the command: `accelerate launch src/f5_tts/train/train.py`.
+        4. Have following error message... (attach logs).
+    validations:
+      required: true
+  - type: textarea
+    attributes:
+      label: ✔️ Expected Behavior
+      placeholder: Describe what you expected to happen.
+    validations:
+      required: false
+  - type: textarea
+    attributes:
+      label: ❌ Actual Behavior
+      placeholder: Describe what actually happened.
+    validations:
+      required: false

.github/ISSUE_TEMPLATE/config.yml

@@ -0,0 +1 @@
+blank_issues_enabled: false

.github/ISSUE_TEMPLATE/feature_request.yml

@@ -0,0 +1,62 @@
+name: "Feature Request"
+description: |
+  Some constructive suggestions and new ideas regarding current repo.
+labels:
+  - enhancement
+body:
+  - type: checkboxes
+    attributes:
+      label: Checks
+      description: "To help us grasp quickly, please confirm the following:"
+      options:
+        - label: This template is only for feature request.
+          required: true
+        - label: I have thoroughly reviewed the project documentation but couldn't find any relevant information that meets my needs.
+          required: true
+        - label: I have searched for existing issues, including closed ones, and found not discussion yet.
+          required: true
+        - label: I confirm that I am using English to submit this report in order to facilitate communication.
+          required: true
+  - type: textarea
+    attributes:
+      label: 1. Is this request related to a challenge you're experiencing? Tell us your story.
+      description: |
+        Describe the specific problem or scenario you're facing in detail. For example:
+        *"I was trying to use [feature] for [specific task], but encountered [issue]. This was frustrating because...."*
+      placeholder: Please describe the situation in as much detail as possible.
+    validations:
+      required: true
+
+  - type: textarea
+    attributes:
+      label: 2. What is your suggested solution?
+      description: |
+        Provide a clear description of the feature or enhancement you'd like to propose. 
+        How would this feature solve your issue or improve the project?
+      placeholder: Describe your idea or proposed solution here.
+    validations:
+      required: true
+
+  - type: textarea
+    attributes:
+      label: 3. Additional context or comments
+      description: |
+        Any other relevant information, links, documents, or screenshots that provide clarity. 
+        Use this section for anything not covered above.
+      placeholder: Add any extra details here.
+    validations:
+      required: false
+
+  - type: checkboxes
+    attributes:
+      label: 4. Can you help us with this feature?
+      description: |
+        Let us know if you're interested in contributing. This is not a commitment but a way to express interest in collaboration.
+      options:
+        - label: I am interested in contributing to this feature.
+          required: false
+
+  - type: markdown
+    attributes:
+      value: |
+        **Note:** Please submit only one request per issue to keep discussions focused and manageable.

.github/ISSUE_TEMPLATE/help_wanted.yml

@@ -0,0 +1,50 @@
+name: "Help Wanted"
+description: |
+  Please provide as much details to help address the issue, including logs and screenshots.
+labels:
+  - help wanted
+body:
+  - type: checkboxes
+    attributes:
+      label: Checks
+      description: "To ensure timely help, please confirm the following:"
+      options:
+        - label: This template is only for usage issues encountered.
+          required: true
+        - label: I have thoroughly reviewed the project documentation but couldn't find information to solve my problem.
+          required: true
+        - label: I have searched for existing issues, including closed ones, and couldn't find a solution.
+          required: true
+        - label: I confirm that I am using English to submit this report in order to facilitate communication.
+          required: true
+  - type: textarea
+    attributes:
+      label: Environment Details
+      description: "Provide details such as OS, Python version, and any relevant software or dependencies."
+      placeholder: e.g., macOS 13.5, Python 3.10, torch==2.3.0, Gradio 4.44.1
+    validations:
+      required: true
+  - type: textarea
+    attributes:
+      label: Steps to Reproduce
+      description: |
+        Include detailed steps, screenshots, and logs. Use the correct markdown syntax for code blocks.
+      placeholder: |
+        1. Create a new conda environment.
+        2. Clone the repository and install as pip package.
+        3. Run the command: `f5-tts_infer-gradio` with no ref_text provided.
+        4. Stuck there with the following message... (attach logs and also error msg e.g. after ctrl-c).
+    validations:
+      required: true
+  - type: textarea
+    attributes:
+      label: ✔️ Expected Behavior
+      placeholder: Describe what you expected to happen, e.g. output a generated audio
+    validations:
+      required: false
+  - type: textarea
+    attributes:
+      label: ❌ Actual Behavior
+      placeholder: Describe what actually happened, failure messages, etc.
+    validations:
+      required: false

.github/ISSUE_TEMPLATE/question.yml

@@ -0,0 +1,26 @@
+name: "Question"
+description: |
+  Pure question or inquiry about the project, usage issue goes with "help wanted".
+labels:
+  - question
+body:
+  - type: checkboxes
+    attributes:
+      label: Checks
+      description: "To help us grasp quickly, please confirm the following:"
+      options:
+        - label: This template is only for question, not feature requests or bug reports.
+          required: true
+        - label: I have thoroughly reviewed the project documentation and read the related paper(s).
+          required: true
+        - label: I have searched for existing issues, including closed ones, no similar questions.
+          required: true
+        - label: I confirm that I am using English to submit this report in order to facilitate communication.
+          required: true
+  - type: textarea
+    attributes:
+      label: Question details
+      description: |
+        Question details, clearly stated using proper markdown syntax.
+    validations:
+      required: true

.github/workflows/pre-commit.yaml

@@ -0,0 +1,14 @@
+name: pre-commit
+
+on:
+  pull_request:
+  push:
+    branches: [main]
+
+jobs:
+  pre-commit:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v3
+      - uses: actions/setup-python@v3
+      - uses: pre-commit/[email protected]

.github/workflows/publish-docker-image.yaml

@@ -0,0 +1,60 @@
+name: Create and publish a Docker image
+
+# Configures this workflow to run every time a change is pushed to the branch called `release`.
+on:
+  push:
+    branches: ['main']
+
+# Defines two custom environment variables for the workflow. These are used for the Container registry domain, and a name for the Docker image that this workflow builds.
+env:
+  REGISTRY: ghcr.io
+  IMAGE_NAME: ${{ github.repository }}
+
+# There is a single job in this workflow. It's configured to run on the latest available version of Ubuntu.
+jobs:
+  build-and-push-image:
+    runs-on: ubuntu-latest
+    # Sets the permissions granted to the `GITHUB_TOKEN` for the actions in this job.
+    permissions:
+      contents: read
+      packages: write
+      # 
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+      - name: Free Up GitHub Actions Ubuntu Runner Disk Space 🔧
+        uses: jlumbroso/free-disk-space@main
+        with:
+          # This might remove tools that are actually needed, if set to "true" but frees about 6 GB
+          tool-cache: false
+
+          # All of these default to true, but feel free to set to "false" if necessary for your workflow
+          android: true
+          dotnet: true
+          haskell: true
+          large-packages: false
+          swap-storage: false
+          docker-images: false
+      # Uses the `docker/login-action` action to log in to the Container registry registry using the account and password that will publish the packages. Once published, the packages are scoped to the account defined here.
+      - name: Log in to the Container registry
+        uses: docker/login-action@65b78e6e13532edd9afa3aa52ac7964289d1a9c1
+        with:
+          registry: ${{ env.REGISTRY }}
+          username: ${{ github.actor }}
+          password: ${{ secrets.GITHUB_TOKEN }}
+      # This step uses [docker/metadata-action](https://github.com/docker/metadata-action#about) to extract tags and labels that will be applied to the specified image. The `id` "meta" allows the output of this step to be referenced in a subsequent step. The `images` value provides the base name for the tags and labels.
+      - name: Extract metadata (tags, labels) for Docker
+        id: meta
+        uses: docker/metadata-action@9ec57ed1fcdbf14dcef7dfbe97b2010124a938b7
+        with:
+          images: ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}
+      # This step uses the `docker/build-push-action` action to build the image, based on your repository's `Dockerfile`. If the build succeeds, it pushes the image to GitHub Packages.
+      # It uses the `context` parameter to define the build's context as the set of files located in the specified path. For more information, see "[Usage](https://github.com/docker/build-push-action#usage)" in the README of the `docker/build-push-action` repository.
+      # It uses the `tags` and `labels` parameters to tag and label the image with the output from the "meta" step.
+      - name: Build and push Docker image
+        uses: docker/build-push-action@f2a1d5e99d037542a71f64918e516c093c6f3fc4
+        with:
+          context: .
+          push: true
+          tags: ${{ steps.meta.outputs.tags }}
+          labels: ${{ steps.meta.outputs.labels }}

.github/workflows/sync-hf.yaml

@@ -0,0 +1,18 @@
+name: Sync to HF Space
+
+on:
+  push:
+    branches:
+      - main
+
+jobs:
+  trigger_curl:
+    runs-on: ubuntu-latest
+
+    steps:
+    - name: Send cURL POST request
+      run: |
+        curl -X POST https://mrfakename-sync-f5.hf.space/gradio_api/call/refresh \
+        -s \
+        -H "Content-Type: application/json" \
+        -d "{\"data\": [\"${{ secrets.REFRESH_PASSWORD }}\"]}"

.gitmodules

@@ -0,0 +1,3 @@
+[submodule "src/third_party/BigVGAN"]
+	path = src/third_party/BigVGAN
+	url = https://github.com/NVIDIA/BigVGAN.git

.pre-commit-config.yaml

@@ -0,0 +1,14 @@
+repos:
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    # Ruff version.
+    rev: v0.7.0
+    hooks:
+      # Run the linter.
+      - id: ruff
+        args: [--fix]
+      # Run the formatter.
+      - id: ruff-format
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v2.3.0
+    hooks:
+      - id: check-yaml

Dockerfile

@@ -0,0 +1,24 @@
+FROM pytorch/pytorch:2.4.0-cuda12.4-cudnn9-devel
+
+USER root
+
+ARG DEBIAN_FRONTEND=noninteractive
+
+LABEL github_repo="https://github.com/SWivid/F5-TTS"
+
+RUN set -x \
+    && apt-get update \
+    && apt-get -y install wget curl man git less openssl libssl-dev unzip unar build-essential aria2 tmux vim \
+    && apt-get install -y openssh-server sox libsox-fmt-all libsox-fmt-mp3 libsndfile1-dev ffmpeg \
+    && rm -rf /var/lib/apt/lists/* \
+    && apt-get clean
+
+WORKDIR /workspace
+
+RUN git clone https://github.com/SWivid/F5-TTS.git \
+    && cd F5-TTS \
+    && pip install -e .[eval]
+
+ENV SHELL=/bin/bash
+
+WORKDIR /workspace/F5-TTS

LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2024 Yushen CHEN
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

README.md

@@ -1,12 +1,13 @@
 ---
-title: F5 TTS
-emoji: 👁
+title: F5-TTS
+emoji: 🗣️
 colorFrom: green
-colorTo: indigo
+colorTo: green
 sdk: gradio
-sdk_version: 5.5.0
 app_file: app.py
-pinned: false
+pinned: true
+short_description: 'F5-TTS & E2-TTS: Zero-Shot Voice Cloning (Unofficial Demo)'
+sdk_version: 4.44.1
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

README_REPO.md

@@ -0,0 +1,172 @@
+# F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching
+
+[![python](https://img.shields.io/badge/Python-3.10-brightgreen)](https://github.com/SWivid/F5-TTS)
+[![arXiv](https://img.shields.io/badge/arXiv-2410.06885-b31b1b.svg?logo=arXiv)](https://arxiv.org/abs/2410.06885)
+[![demo](https://img.shields.io/badge/GitHub-Demo%20page-orange.svg)](https://swivid.github.io/F5-TTS/)
+[![hfspace](https://img.shields.io/badge/🤗-Space%20demo-yellow)](https://huggingface.co/spaces/mrfakename/E2-F5-TTS)
+[![msspace](https://img.shields.io/badge/🤖-Space%20demo-blue)](https://modelscope.cn/studios/modelscope/E2-F5-TTS)
+[![lab](https://img.shields.io/badge/X--LANCE-Lab-grey?labelColor=lightgrey)](https://x-lance.sjtu.edu.cn/)
+<img src="https://github.com/user-attachments/assets/12d7749c-071a-427c-81bf-b87b91def670" alt="Watermark" style="width: 40px; height: auto">
+
+**F5-TTS**: Diffusion Transformer with ConvNeXt V2, faster trained and inference.
+
+**E2 TTS**: Flat-UNet Transformer, closest reproduction from [paper](https://arxiv.org/abs/2406.18009).
+
+**Sway Sampling**: Inference-time flow step sampling strategy, greatly improves performance
+
+### Thanks to all the contributors !
+
+## News
+- **2024/10/08**: F5-TTS & E2 TTS base models on [🤗 Hugging Face](https://huggingface.co/SWivid/F5-TTS), [🤖 Model Scope](https://www.modelscope.cn/models/SWivid/F5-TTS_Emilia-ZH-EN), [🟣 Wisemodel](https://wisemodel.cn/models/SJTU_X-LANCE/F5-TTS_Emilia-ZH-EN).
+
+## Installation
+
+```bash
+# Create a python 3.10 conda env (you could also use virtualenv)
+conda create -n f5-tts python=3.10
+conda activate f5-tts
+
+# Install pytorch with your CUDA version, e.g.
+pip install torch==2.3.0+cu118 torchaudio==2.3.0+cu118 --extra-index-url https://download.pytorch.org/whl/cu118
+```
+
+Then you can choose from a few options below:
+
+### 1. As a pip package (if just for inference)
+
+```bash
+pip install git+https://github.com/SWivid/F5-TTS.git
+```
+
+### 2. Local editable (if also do training, finetuning)
+
+```bash
+git clone https://github.com/SWivid/F5-TTS.git
+cd F5-TTS
+# git submodule update --init --recursive  # (optional, if need bigvgan)
+pip install -e .
+```
+If initialize submodule, you should add the following code at the beginning of `src/third_party/BigVGAN/bigvgan.py`.
+```python
+import os
+import sys
+sys.path.append(os.path.dirname(os.path.abspath(__file__)))
+```
+
+### 3. Docker usage
+```bash
+# Build from Dockerfile
+docker build -t f5tts:v1 .
+
+# Or pull from GitHub Container Registry
+docker pull ghcr.io/swivid/f5-tts:main
+```
+
+
+## Inference
+
+### 1. Gradio App
+
+Currently supported features:
+
+- Basic TTS with Chunk Inference
+- Multi-Style / Multi-Speaker Generation
+- Voice Chat powered by Qwen2.5-3B-Instruct
+- [Custom model](src/f5_tts/infer/SHARED.md) inference (local only)
+
+```bash
+# Launch a Gradio app (web interface)
+f5-tts_infer-gradio
+
+# Specify the port/host
+f5-tts_infer-gradio --port 7860 --host 0.0.0.0
+
+# Launch a share link
+f5-tts_infer-gradio --share
+```
+
+### 2. CLI Inference
+
+```bash
+# Run with flags
+# Leave --ref_text "" will have ASR model transcribe (extra GPU memory usage)
+f5-tts_infer-cli \
+--model "F5-TTS" \
+--ref_audio "ref_audio.wav" \
+--ref_text "The content, subtitle or transcription of reference audio." \
+--gen_text "Some text you want TTS model generate for you."
+
+# Run with default setting. src/f5_tts/infer/examples/basic/basic.toml
+f5-tts_infer-cli
+# Or with your own .toml file
+f5-tts_infer-cli -c custom.toml
+
+# Multi voice. See src/f5_tts/infer/README.md
+f5-tts_infer-cli -c src/f5_tts/infer/examples/multi/story.toml
+```
+
+### 3. More instructions
+
+- In order to have better generation results, take a moment to read [detailed guidance](src/f5_tts/infer).
+- The [Issues](https://github.com/SWivid/F5-TTS/issues?q=is%3Aissue) are very useful, please try to find the solution by properly searching the keywords of problem encountered. If no answer found, then feel free to open an issue.
+
+
+## Training
+
+### 1. Gradio App
+
+Read [training & finetuning guidance](src/f5_tts/train) for more instructions.
+
+```bash
+# Quick start with Gradio web interface
+f5-tts_finetune-gradio
+```
+
+
+## [Evaluation](src/f5_tts/eval)
+
+
+## Development
+
+Use pre-commit to ensure code quality (will run linters and formatters automatically)
+
+```bash
+pip install pre-commit
+pre-commit install
+```
+
+When making a pull request, before each commit, run: 
+
+```bash
+pre-commit run --all-files
+```
+
+Note: Some model components have linting exceptions for E722 to accommodate tensor notation
+
+
+## Acknowledgements
+
+- [E2-TTS](https://arxiv.org/abs/2406.18009) brilliant work, simple and effective
+- [Emilia](https://arxiv.org/abs/2407.05361), [WenetSpeech4TTS](https://arxiv.org/abs/2406.05763) valuable datasets
+- [lucidrains](https://github.com/lucidrains) initial CFM structure with also [bfs18](https://github.com/bfs18) for discussion
+- [SD3](https://arxiv.org/abs/2403.03206) & [Hugging Face diffusers](https://github.com/huggingface/diffusers) DiT and MMDiT code structure
+- [torchdiffeq](https://github.com/rtqichen/torchdiffeq) as ODE solver, [Vocos](https://huggingface.co/charactr/vocos-mel-24khz) as vocoder
+- [FunASR](https://github.com/modelscope/FunASR), [faster-whisper](https://github.com/SYSTRAN/faster-whisper), [UniSpeech](https://github.com/microsoft/UniSpeech) for evaluation tools
+- [ctc-forced-aligner](https://github.com/MahmoudAshraf97/ctc-forced-aligner) for speech edit test
+- [mrfakename](https://x.com/realmrfakename) huggingface space demo ~
+- [f5-tts-mlx](https://github.com/lucasnewman/f5-tts-mlx/tree/main) Implementation with MLX framework by [Lucas Newman](https://github.com/lucasnewman)
+- [F5-TTS-ONNX](https://github.com/DakeQQ/F5-TTS-ONNX) ONNX Runtime version by [DakeQQ](https://github.com/DakeQQ)
+
+## Citation
+If our work and codebase is useful for you, please cite as:
+```
+@article{chen-etal-2024-f5tts,
+      title={F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching}, 
+      author={Yushen Chen and Zhikang Niu and Ziyang Ma and Keqi Deng and Chunhui Wang and Jian Zhao and Kai Yu and Xie Chen},
+      journal={arXiv preprint arXiv:2410.06885},
+      year={2024},
+}
+```
+## License
+
+Our code is released under MIT License. The pre-trained models are licensed under the CC-BY-NC license due to the training data Emilia, which is an in-the-wild dataset. Sorry for any inconvenience this may cause.

api.py

@@ -0,0 +1,132 @@
+import soundfile as sf
+import torch
+import tqdm
+from cached_path import cached_path
+
+from model import DiT, UNetT
+from model.utils import save_spectrogram
+
+from model.utils_infer import load_vocoder, load_model, infer_process, remove_silence_for_generated_wav
+from model.utils import seed_everything
+import random
+import sys
+
+
+class F5TTS:
+    def __init__(
+        self,
+        model_type="F5-TTS",
+        ckpt_file="",
+        vocab_file="",
+        ode_method="euler",
+        use_ema=True,
+        local_path=None,
+        device=None,
+    ):
+        # Initialize parameters
+        self.final_wave = None
+        self.target_sample_rate = 24000
+        self.n_mel_channels = 100
+        self.hop_length = 256
+        self.target_rms = 0.1
+        self.seed = -1
+
+        # Set device
+        self.device = device or (
+            "cuda" if torch.cuda.is_available() else "mps" if torch.backends.mps.is_available() else "cpu"
+        )
+
+        # Load models
+        self.load_vocoder_model(local_path)
+        self.load_ema_model(model_type, ckpt_file, vocab_file, ode_method, use_ema)
+
+    def load_vocoder_model(self, local_path):
+        self.vocos = load_vocoder(local_path is not None, local_path, self.device)
+
+    def load_ema_model(self, model_type, ckpt_file, vocab_file, ode_method, use_ema):
+        if model_type == "F5-TTS":
+            if not ckpt_file:
+                ckpt_file = str(cached_path("hf://SWivid/F5-TTS/F5TTS_Base/model_1200000.safetensors"))
+            model_cfg = dict(dim=1024, depth=22, heads=16, ff_mult=2, text_dim=512, conv_layers=4)
+            model_cls = DiT
+        elif model_type == "E2-TTS":
+            if not ckpt_file:
+                ckpt_file = str(cached_path("hf://SWivid/E2-TTS/E2TTS_Base/model_1200000.safetensors"))
+            model_cfg = dict(dim=1024, depth=24, heads=16, ff_mult=4)
+            model_cls = UNetT
+        else:
+            raise ValueError(f"Unknown model type: {model_type}")
+
+        self.ema_model = load_model(model_cls, model_cfg, ckpt_file, vocab_file, ode_method, use_ema, self.device)
+
+    def export_wav(self, wav, file_wave, remove_silence=False):
+        sf.write(file_wave, wav, self.target_sample_rate)
+
+        if remove_silence:
+            remove_silence_for_generated_wav(file_wave)
+
+    def export_spectrogram(self, spect, file_spect):
+        save_spectrogram(spect, file_spect)
+
+    def infer(
+        self,
+        ref_file,
+        ref_text,
+        gen_text,
+        show_info=print,
+        progress=tqdm,
+        target_rms=0.1,
+        cross_fade_duration=0.15,
+        sway_sampling_coef=-1,
+        cfg_strength=2,
+        nfe_step=32,
+        speed=1.0,
+        fix_duration=None,
+        remove_silence=False,
+        file_wave=None,
+        file_spect=None,
+        seed=-1,
+    ):
+        if seed == -1:
+            seed = random.randint(0, sys.maxsize)
+        seed_everything(seed)
+        self.seed = seed
+        wav, sr, spect = infer_process(
+            ref_file,
+            ref_text,
+            gen_text,
+            self.ema_model,
+            show_info=show_info,
+            progress=progress,
+            target_rms=target_rms,
+            cross_fade_duration=cross_fade_duration,
+            nfe_step=nfe_step,
+            cfg_strength=cfg_strength,
+            sway_sampling_coef=sway_sampling_coef,
+            speed=speed,
+            fix_duration=fix_duration,
+            device=self.device,
+        )
+
+        if file_wave is not None:
+            self.export_wav(wav, file_wave, remove_silence)
+
+        if file_spect is not None:
+            self.export_spectrogram(spect, file_spect)
+
+        return wav, sr, spect
+
+
+if __name__ == "__main__":
+    f5tts = F5TTS()
+
+    wav, sr, spect = f5tts.infer(
+        ref_file="tests/ref_audio/test_en_1_ref_short.wav",
+        ref_text="some call me nature, others call me mother nature.",
+        gen_text="""I don't really care what you call me. I've been a silent spectator, watching species evolve, empires rise and fall. But always remember, I am mighty and enduring. Respect me and I'll nurture you; ignore me and you shall face the consequences.""",
+        file_wave="tests/out.wav",
+        file_spect="tests/out.png",
+        seed=-1,  # random seed = -1
+    )
+
+    print("seed :", f5tts.seed)

app.py

@@ -0,0 +1,844 @@
+# ruff: noqa: E402
+# Above allows ruff to ignore E402: module level import not at top of file
+
+import re
+import tempfile
+from collections import OrderedDict
+from importlib.resources import files
+
+import click
+import gradio as gr
+import numpy as np
+import soundfile as sf
+import torchaudio
+from cached_path import cached_path
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+try:
+    import spaces
+
+    USING_SPACES = True
+except ImportError:
+    USING_SPACES = False
+
+
+def gpu_decorator(func):
+    if USING_SPACES:
+        return spaces.GPU(func)
+    else:
+        return func
+
+
+from f5_tts.model import DiT, UNetT
+from f5_tts.infer.utils_infer import (
+    load_vocoder,
+    load_model,
+    preprocess_ref_audio_text,
+    infer_process,
+    remove_silence_for_generated_wav,
+    save_spectrogram,
+)
+
+
+DEFAULT_TTS_MODEL = "F5-TTS"
+tts_model_choice = DEFAULT_TTS_MODEL
+
+
+# load models
+
+vocoder = load_vocoder()
+
+
+def load_f5tts(ckpt_path=str(cached_path("hf://SWivid/F5-TTS/F5TTS_Base/model_1200000.safetensors"))):
+    F5TTS_model_cfg = dict(dim=1024, depth=22, heads=16, ff_mult=2, text_dim=512, conv_layers=4)
+    return load_model(DiT, F5TTS_model_cfg, ckpt_path)
+
+
+def load_e2tts(ckpt_path=str(cached_path("hf://SWivid/E2-TTS/E2TTS_Base/model_1200000.safetensors"))):
+    E2TTS_model_cfg = dict(dim=1024, depth=24, heads=16, ff_mult=4)
+    return load_model(UNetT, E2TTS_model_cfg, ckpt_path)
+
+
+def load_custom(ckpt_path: str, vocab_path="", model_cfg=None):
+    ckpt_path, vocab_path = ckpt_path.strip(), vocab_path.strip()
+    if ckpt_path.startswith("hf://"):
+        ckpt_path = str(cached_path(ckpt_path))
+    if vocab_path.startswith("hf://"):
+        vocab_path = str(cached_path(vocab_path))
+    if model_cfg is None:
+        model_cfg = dict(dim=1024, depth=22, heads=16, ff_mult=2, text_dim=512, conv_layers=4)
+    return load_model(DiT, model_cfg, ckpt_path, vocab_file=vocab_path)
+
+
+F5TTS_ema_model = load_f5tts()
+E2TTS_ema_model = load_e2tts() if USING_SPACES else None
+custom_ema_model, pre_custom_path = None, ""
+
+chat_model_state = None
+chat_tokenizer_state = None
+
+
+@gpu_decorator
+def generate_response(messages, model, tokenizer):
+    """Generate response using Qwen"""
+    text = tokenizer.apply_chat_template(
+        messages,
+        tokenize=False,
+        add_generation_prompt=True,
+    )
+
+    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
+    generated_ids = model.generate(
+        **model_inputs,
+        max_new_tokens=512,
+        temperature=0.7,
+        top_p=0.95,
+    )
+
+    generated_ids = [
+        output_ids[len(input_ids) :] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
+    ]
+    return tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
+
+
+@gpu_decorator
+def infer(
+    ref_audio_orig, ref_text, gen_text, model, remove_silence, cross_fade_duration=0.15, speed=1, show_info=gr.Info
+):
+    ref_audio, ref_text = preprocess_ref_audio_text(ref_audio_orig, ref_text, show_info=show_info)
+
+    if model == "F5-TTS":
+        ema_model = F5TTS_ema_model
+    elif model == "E2-TTS":
+        global E2TTS_ema_model
+        if E2TTS_ema_model is None:
+            show_info("Loading E2-TTS model...")
+            E2TTS_ema_model = load_e2tts()
+        ema_model = E2TTS_ema_model
+    elif isinstance(model, list) and model[0] == "Custom":
+        assert not USING_SPACES, "Only official checkpoints allowed in Spaces."
+        global custom_ema_model, pre_custom_path
+        if pre_custom_path != model[1]:
+            show_info("Loading Custom TTS model...")
+            custom_ema_model = load_custom(model[1], vocab_path=model[2])
+            pre_custom_path = model[1]
+        ema_model = custom_ema_model
+
+    final_wave, final_sample_rate, combined_spectrogram = infer_process(
+        ref_audio,
+        ref_text,
+        gen_text,
+        ema_model,
+        vocoder,
+        cross_fade_duration=cross_fade_duration,
+        speed=speed,
+        show_info=show_info,
+        progress=gr.Progress(),
+    )
+
+    # Remove silence
+    if remove_silence:
+        with tempfile.NamedTemporaryFile(delete=False, suffix=".wav") as f:
+            sf.write(f.name, final_wave, final_sample_rate)
+            remove_silence_for_generated_wav(f.name)
+            final_wave, _ = torchaudio.load(f.name)
+        final_wave = final_wave.squeeze().cpu().numpy()
+
+    # Save the spectrogram
+    with tempfile.NamedTemporaryFile(suffix=".png", delete=False) as tmp_spectrogram:
+        spectrogram_path = tmp_spectrogram.name
+        save_spectrogram(combined_spectrogram, spectrogram_path)
+
+    return (final_sample_rate, final_wave), spectrogram_path, ref_text
+
+
+with gr.Blocks() as app_credits:
+    gr.Markdown("""
+# Credits
+
+* [mrfakename](https://github.com/fakerybakery) for the original [online demo](https://huggingface.co/spaces/mrfakename/E2-F5-TTS)
+* [RootingInLoad](https://github.com/RootingInLoad) for initial chunk generation and podcast app exploration
+* [jpgallegoar](https://github.com/jpgallegoar) for multiple speech-type generation & voice chat
+""")
+with gr.Blocks() as app_tts:
+    gr.Markdown("# Batched TTS")
+    ref_audio_input = gr.Audio(label="Reference Audio", type="filepath")
+    gen_text_input = gr.Textbox(label="Text to Generate", lines=10)
+    generate_btn = gr.Button("Synthesize", variant="primary")
+    with gr.Accordion("Advanced Settings", open=False):
+        ref_text_input = gr.Textbox(
+            label="Reference Text",
+            info="Leave blank to automatically transcribe the reference audio. If you enter text it will override automatic transcription.",
+            lines=2,
+        )
+        remove_silence = gr.Checkbox(
+            label="Remove Silences",
+            info="The model tends to produce silences, especially on longer audio. We can manually remove silences if needed. Note that this is an experimental feature and may produce strange results. This will also increase generation time.",
+            value=False,
+        )
+        speed_slider = gr.Slider(
+            label="Speed",
+            minimum=0.3,
+            maximum=2.0,
+            value=1.0,
+            step=0.1,
+            info="Adjust the speed of the audio.",
+        )
+        cross_fade_duration_slider = gr.Slider(
+            label="Cross-Fade Duration (s)",
+            minimum=0.0,
+            maximum=1.0,
+            value=0.15,
+            step=0.01,
+            info="Set the duration of the cross-fade between audio clips.",
+        )
+
+    audio_output = gr.Audio(label="Synthesized Audio")
+    spectrogram_output = gr.Image(label="Spectrogram")
+
+    @gpu_decorator
+    def basic_tts(
+        ref_audio_input,
+        ref_text_input,
+        gen_text_input,
+        remove_silence,
+        cross_fade_duration_slider,
+        speed_slider,
+    ):
+        audio_out, spectrogram_path, ref_text_out = infer(
+            ref_audio_input,
+            ref_text_input,
+            gen_text_input,
+            tts_model_choice,
+            remove_silence,
+            cross_fade_duration_slider,
+            speed_slider,
+        )
+        return audio_out, spectrogram_path, gr.update(value=ref_text_out)
+
+    generate_btn.click(
+        basic_tts,
+        inputs=[
+            ref_audio_input,
+            ref_text_input,
+            gen_text_input,
+            remove_silence,
+            cross_fade_duration_slider,
+            speed_slider,
+        ],
+        outputs=[audio_output, spectrogram_output, ref_text_input],
+    )
+
+
+def parse_speechtypes_text(gen_text):
+    # Pattern to find {speechtype}
+    pattern = r"\{(.*?)\}"
+
+    # Split the text by the pattern
+    tokens = re.split(pattern, gen_text)
+
+    segments = []
+
+    current_style = "Regular"
+
+    for i in range(len(tokens)):
+        if i % 2 == 0:
+            # This is text
+            text = tokens[i].strip()
+            if text:
+                segments.append({"style": current_style, "text": text})
+        else:
+            # This is style
+            style = tokens[i].strip()
+            current_style = style
+
+    return segments
+
+
+with gr.Blocks() as app_multistyle:
+    # New section for multistyle generation
+    gr.Markdown(
+        """
+    # Multiple Speech-Type Generation
+
+    This section allows you to generate multiple speech types or multiple people's voices. Enter your text in the format shown below, and the system will generate speech using the appropriate type. If unspecified, the model will use the regular speech type. The current speech type will be used until the next speech type is specified.
+    """
+    )
+
+    with gr.Row():
+        gr.Markdown(
+            """
+            **Example Input:**                                                                      
+            {Regular} Hello, I'd like to order a sandwich please.                                                         
+            {Surprised} What do you mean you're out of bread?                                                                      
+            {Sad} I really wanted a sandwich though...                                                              
+            {Angry} You know what, darn you and your little shop!                                                                       
+            {Whisper} I'll just go back home and cry now.                                                                           
+            {Shouting} Why me?!                                                                         
+            """
+        )
+
+        gr.Markdown(
+            """
+            **Example Input 2:**                                                                                
+            {Speaker1_Happy} Hello, I'd like to order a sandwich please.                                                            
+            {Speaker2_Regular} Sorry, we're out of bread.                                                                                
+            {Speaker1_Sad} I really wanted a sandwich though...                                                                             
+            {Speaker2_Whisper} I'll give you the last one I was hiding.                                                                     
+            """
+        )
+
+    gr.Markdown(
+        "Upload different audio clips for each speech type. The first speech type is mandatory. You can add additional speech types by clicking the 'Add Speech Type' button."
+    )
+
+    # Regular speech type (mandatory)
+    with gr.Row():
+        with gr.Column():
+            regular_name = gr.Textbox(value="Regular", label="Speech Type Name")
+            regular_insert = gr.Button("Insert Label", variant="secondary")
+        regular_audio = gr.Audio(label="Regular Reference Audio", type="filepath")
+        regular_ref_text = gr.Textbox(label="Reference Text (Regular)", lines=2)
+
+    # Regular speech type (max 100)
+    max_speech_types = 100
+    speech_type_rows = []  # 99
+    speech_type_names = [regular_name]  # 100
+    speech_type_audios = [regular_audio]  # 100
+    speech_type_ref_texts = [regular_ref_text]  # 100
+    speech_type_delete_btns = []  # 99
+    speech_type_insert_btns = [regular_insert]  # 100
+
+    # Additional speech types (99 more)
+    for i in range(max_speech_types - 1):
+        with gr.Row(visible=False) as row:
+            with gr.Column():
+                name_input = gr.Textbox(label="Speech Type Name")
+                delete_btn = gr.Button("Delete Type", variant="secondary")
+                insert_btn = gr.Button("Insert Label", variant="secondary")
+            audio_input = gr.Audio(label="Reference Audio", type="filepath")
+            ref_text_input = gr.Textbox(label="Reference Text", lines=2)
+        speech_type_rows.append(row)
+        speech_type_names.append(name_input)
+        speech_type_audios.append(audio_input)
+        speech_type_ref_texts.append(ref_text_input)
+        speech_type_delete_btns.append(delete_btn)
+        speech_type_insert_btns.append(insert_btn)
+
+    # Button to add speech type
+    add_speech_type_btn = gr.Button("Add Speech Type")
+
+    # Keep track of current number of speech types
+    speech_type_count = gr.State(value=1)
+
+    # Function to add a speech type
+    def add_speech_type_fn(speech_type_count):
+        if speech_type_count < max_speech_types:
+            speech_type_count += 1
+            # Prepare updates for the rows
+            row_updates = []
+            for i in range(1, max_speech_types):
+                if i < speech_type_count:
+                    row_updates.append(gr.update(visible=True))
+                else:
+                    row_updates.append(gr.update())
+        else:
+            # Optionally, show a warning
+            row_updates = [gr.update() for _ in range(1, max_speech_types)]
+        return [speech_type_count] + row_updates
+
+    add_speech_type_btn.click(
+        add_speech_type_fn, inputs=speech_type_count, outputs=[speech_type_count] + speech_type_rows
+    )
+
+    # Function to delete a speech type
+    def make_delete_speech_type_fn(index):
+        def delete_speech_type_fn(speech_type_count):
+            # Prepare updates
+            row_updates = []
+
+            for i in range(1, max_speech_types):
+                if i == index:
+                    row_updates.append(gr.update(visible=False))
+                else:
+                    row_updates.append(gr.update())
+
+            speech_type_count = max(1, speech_type_count)
+
+            return [speech_type_count] + row_updates
+
+        return delete_speech_type_fn
+
+    # Update delete button clicks
+    for i, delete_btn in enumerate(speech_type_delete_btns):
+        delete_fn = make_delete_speech_type_fn(i)
+        delete_btn.click(delete_fn, inputs=speech_type_count, outputs=[speech_type_count] + speech_type_rows)
+
+    # Text input for the prompt
+    gen_text_input_multistyle = gr.Textbox(
+        label="Text to Generate",
+        lines=10,
+        placeholder="Enter the script with speaker names (or emotion types) at the start of each block, e.g.:\n\n{Regular} Hello, I'd like to order a sandwich please.\n{Surprised} What do you mean you're out of bread?\n{Sad} I really wanted a sandwich though...\n{Angry} You know what, darn you and your little shop!\n{Whisper} I'll just go back home and cry now.\n{Shouting} Why me?!",
+    )
+
+    def make_insert_speech_type_fn(index):
+        def insert_speech_type_fn(current_text, speech_type_name):
+            current_text = current_text or ""
+            speech_type_name = speech_type_name or "None"
+            updated_text = current_text + f"{{{speech_type_name}}} "
+            return gr.update(value=updated_text)
+
+        return insert_speech_type_fn
+
+    for i, insert_btn in enumerate(speech_type_insert_btns):
+        insert_fn = make_insert_speech_type_fn(i)
+        insert_btn.click(
+            insert_fn,
+            inputs=[gen_text_input_multistyle, speech_type_names[i]],
+            outputs=gen_text_input_multistyle,
+        )
+
+    with gr.Accordion("Advanced Settings", open=False):
+        remove_silence_multistyle = gr.Checkbox(
+            label="Remove Silences",
+            value=True,
+        )
+
+    # Generate button
+    generate_multistyle_btn = gr.Button("Generate Multi-Style Speech", variant="primary")
+
+    # Output audio
+    audio_output_multistyle = gr.Audio(label="Synthesized Audio")
+
+    @gpu_decorator
+    def generate_multistyle_speech(
+        gen_text,
+        *args,
+    ):
+        speech_type_names_list = args[:max_speech_types]
+        speech_type_audios_list = args[max_speech_types : 2 * max_speech_types]
+        speech_type_ref_texts_list = args[2 * max_speech_types : 3 * max_speech_types]
+        remove_silence = args[3 * max_speech_types]
+        # Collect the speech types and their audios into a dict
+        speech_types = OrderedDict()
+
+        ref_text_idx = 0
+        for name_input, audio_input, ref_text_input in zip(
+            speech_type_names_list, speech_type_audios_list, speech_type_ref_texts_list
+        ):
+            if name_input and audio_input:
+                speech_types[name_input] = {"audio": audio_input, "ref_text": ref_text_input}
+            else:
+                speech_types[f"@{ref_text_idx}@"] = {"audio": "", "ref_text": ""}
+            ref_text_idx += 1
+
+        # Parse the gen_text into segments
+        segments = parse_speechtypes_text(gen_text)
+
+        # For each segment, generate speech
+        generated_audio_segments = []
+        current_style = "Regular"
+
+        for segment in segments:
+            style = segment["style"]
+            text = segment["text"]
+
+            if style in speech_types:
+                current_style = style
+            else:
+                # If style not available, default to Regular
+                current_style = "Regular"
+
+            ref_audio = speech_types[current_style]["audio"]
+            ref_text = speech_types[current_style].get("ref_text", "")
+
+            # Generate speech for this segment
+            audio_out, _, ref_text_out = infer(
+                ref_audio, ref_text, text, tts_model_choice, remove_silence, 0, show_info=print
+            )  # show_info=print no pull to top when generating
+            sr, audio_data = audio_out
+
+            generated_audio_segments.append(audio_data)
+            speech_types[current_style]["ref_text"] = ref_text_out
+
+        # Concatenate all audio segments
+        if generated_audio_segments:
+            final_audio_data = np.concatenate(generated_audio_segments)
+            return [(sr, final_audio_data)] + [
+                gr.update(value=speech_types[style]["ref_text"]) for style in speech_types
+            ]
+        else:
+            gr.Warning("No audio generated.")
+            return [None] + [gr.update(value=speech_types[style]["ref_text"]) for style in speech_types]
+
+    generate_multistyle_btn.click(
+        generate_multistyle_speech,
+        inputs=[
+            gen_text_input_multistyle,
+        ]
+        + speech_type_names
+        + speech_type_audios
+        + speech_type_ref_texts
+        + [
+            remove_silence_multistyle,
+        ],
+        outputs=[audio_output_multistyle] + speech_type_ref_texts,
+    )
+
+    # Validation function to disable Generate button if speech types are missing
+    def validate_speech_types(gen_text, regular_name, *args):
+        speech_type_names_list = args[:max_speech_types]
+
+        # Collect the speech types names
+        speech_types_available = set()
+        if regular_name:
+            speech_types_available.add(regular_name)
+        for name_input in speech_type_names_list:
+            if name_input:
+                speech_types_available.add(name_input)
+
+        # Parse the gen_text to get the speech types used
+        segments = parse_speechtypes_text(gen_text)
+        speech_types_in_text = set(segment["style"] for segment in segments)
+
+        # Check if all speech types in text are available
+        missing_speech_types = speech_types_in_text - speech_types_available
+
+        if missing_speech_types:
+            # Disable the generate button
+            return gr.update(interactive=False)
+        else:
+            # Enable the generate button
+            return gr.update(interactive=True)
+
+    gen_text_input_multistyle.change(
+        validate_speech_types,
+        inputs=[gen_text_input_multistyle, regular_name] + speech_type_names,
+        outputs=generate_multistyle_btn,
+    )
+
+
+with gr.Blocks() as app_chat:
+    gr.Markdown(
+        """
+# Voice Chat
+Have a conversation with an AI using your reference voice! 
+1. Upload a reference audio clip and optionally its transcript.
+2. Load the chat model.
+3. Record your message through your microphone.
+4. The AI will respond using the reference voice.
+"""
+    )
+
+    if not USING_SPACES:
+        load_chat_model_btn = gr.Button("Load Chat Model", variant="primary")
+
+        chat_interface_container = gr.Column(visible=False)
+
+        @gpu_decorator
+        def load_chat_model():
+            global chat_model_state, chat_tokenizer_state
+            if chat_model_state is None:
+                show_info = gr.Info
+                show_info("Loading chat model...")
+                model_name = "Qwen/Qwen2.5-3B-Instruct"
+                chat_model_state = AutoModelForCausalLM.from_pretrained(
+                    model_name, torch_dtype="auto", device_map="auto"
+                )
+                chat_tokenizer_state = AutoTokenizer.from_pretrained(model_name)
+                show_info("Chat model loaded.")
+
+            return gr.update(visible=False), gr.update(visible=True)
+
+        load_chat_model_btn.click(load_chat_model, outputs=[load_chat_model_btn, chat_interface_container])
+
+    else:
+        chat_interface_container = gr.Column()
+
+        if chat_model_state is None:
+            model_name = "Qwen/Qwen2.5-3B-Instruct"
+            chat_model_state = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype="auto", device_map="auto")
+            chat_tokenizer_state = AutoTokenizer.from_pretrained(model_name)
+
+    with chat_interface_container:
+        with gr.Row():
+            with gr.Column():
+                ref_audio_chat = gr.Audio(label="Reference Audio", type="filepath")
+            with gr.Column():
+                with gr.Accordion("Advanced Settings", open=False):
+                    remove_silence_chat = gr.Checkbox(
+                        label="Remove Silences",
+                        value=True,
+                    )
+                    ref_text_chat = gr.Textbox(
+                        label="Reference Text",
+                        info="Optional: Leave blank to auto-transcribe",
+                        lines=2,
+                    )
+                    system_prompt_chat = gr.Textbox(
+                        label="System Prompt",
+                        value="You are not an AI assistant, you are whoever the user says you are. You must stay in character. Keep your responses concise since they will be spoken out loud.",
+                        lines=2,
+                    )
+
+        chatbot_interface = gr.Chatbot(label="Conversation")
+
+        with gr.Row():
+            with gr.Column():
+                audio_input_chat = gr.Microphone(
+                    label="Speak your message",
+                    type="filepath",
+                )
+                audio_output_chat = gr.Audio(autoplay=True)
+            with gr.Column():
+                text_input_chat = gr.Textbox(
+                    label="Type your message",
+                    lines=1,
+                )
+                send_btn_chat = gr.Button("Send Message")
+                clear_btn_chat = gr.Button("Clear Conversation")
+
+        conversation_state = gr.State(
+            value=[
+                {
+                    "role": "system",
+                    "content": "You are not an AI assistant, you are whoever the user says you are. You must stay in character. Keep your responses concise since they will be spoken out loud.",
+                }
+            ]
+        )
+
+        # Modify process_audio_input to use model and tokenizer from state
+        @gpu_decorator
+        def process_audio_input(audio_path, text, history, conv_state):
+            """Handle audio or text input from user"""
+
+            if not audio_path and not text.strip():
+                return history, conv_state, ""
+
+            if audio_path:
+                text = preprocess_ref_audio_text(audio_path, text)[1]
+
+            if not text.strip():
+                return history, conv_state, ""
+
+            conv_state.append({"role": "user", "content": text})
+            history.append((text, None))
+
+            response = generate_response(conv_state, chat_model_state, chat_tokenizer_state)
+
+            conv_state.append({"role": "assistant", "content": response})
+            history[-1] = (text, response)
+
+            return history, conv_state, ""
+
+        @gpu_decorator
+        def generate_audio_response(history, ref_audio, ref_text, remove_silence):
+            """Generate TTS audio for AI response"""
+            if not history or not ref_audio:
+                return None
+
+            last_user_message, last_ai_response = history[-1]
+            if not last_ai_response:
+                return None
+
+            audio_result, _, ref_text_out = infer(
+                ref_audio,
+                ref_text,
+                last_ai_response,
+                tts_model_choice,
+                remove_silence,
+                cross_fade_duration=0.15,
+                speed=1.0,
+                show_info=print,  # show_info=print no pull to top when generating
+            )
+            return audio_result, gr.update(value=ref_text_out)
+
+        def clear_conversation():
+            """Reset the conversation"""
+            return [], [
+                {
+                    "role": "system",
+                    "content": "You are not an AI assistant, you are whoever the user says you are. You must stay in character. Keep your responses concise since they will be spoken out loud.",
+                }
+            ]
+
+        def update_system_prompt(new_prompt):
+            """Update the system prompt and reset the conversation"""
+            new_conv_state = [{"role": "system", "content": new_prompt}]
+            return [], new_conv_state
+
+        # Handle audio input
+        audio_input_chat.stop_recording(
+            process_audio_input,
+            inputs=[audio_input_chat, text_input_chat, chatbot_interface, conversation_state],
+            outputs=[chatbot_interface, conversation_state],
+        ).then(
+            generate_audio_response,
+            inputs=[chatbot_interface, ref_audio_chat, ref_text_chat, remove_silence_chat],
+            outputs=[audio_output_chat, ref_text_chat],
+        ).then(
+            lambda: None,
+            None,
+            audio_input_chat,
+        )
+
+        # Handle text input
+        text_input_chat.submit(
+            process_audio_input,
+            inputs=[audio_input_chat, text_input_chat, chatbot_interface, conversation_state],
+            outputs=[chatbot_interface, conversation_state],
+        ).then(
+            generate_audio_response,
+            inputs=[chatbot_interface, ref_audio_chat, ref_text_chat, remove_silence_chat],
+            outputs=[audio_output_chat, ref_text_chat],
+        ).then(
+            lambda: None,
+            None,
+            text_input_chat,
+        )
+
+        # Handle send button
+        send_btn_chat.click(
+            process_audio_input,
+            inputs=[audio_input_chat, text_input_chat, chatbot_interface, conversation_state],
+            outputs=[chatbot_interface, conversation_state],
+        ).then(
+            generate_audio_response,
+            inputs=[chatbot_interface, ref_audio_chat, ref_text_chat, remove_silence_chat],
+            outputs=[audio_output_chat, ref_text_chat],
+        ).then(
+            lambda: None,
+            None,
+            text_input_chat,
+        )
+
+        # Handle clear button
+        clear_btn_chat.click(
+            clear_conversation,
+            outputs=[chatbot_interface, conversation_state],
+        )
+
+        # Handle system prompt change and reset conversation
+        system_prompt_chat.change(
+            update_system_prompt,
+            inputs=system_prompt_chat,
+            outputs=[chatbot_interface, conversation_state],
+        )
+
+
+with gr.Blocks() as app:
+    gr.Markdown(
+        """
+# E2/F5 TTS
+
+This is a local web UI for F5 TTS with advanced batch processing support. This app supports the following TTS models:
+
+* [F5-TTS](https://arxiv.org/abs/2410.06885) (A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching)
+* [E2 TTS](https://arxiv.org/abs/2406.18009) (Embarrassingly Easy Fully Non-Autoregressive Zero-Shot TTS)
+
+The checkpoints currently support English and Chinese.
+
+If you're having issues, try converting your reference audio to WAV or MP3, clipping it to 15s with  ✂  in the bottom right corner (otherwise might have non-optimal auto-trimmed result).
+
+**NOTE: Reference text will be automatically transcribed with Whisper if not provided. For best results, keep your reference clips short (<15s). Ensure the audio is fully uploaded before generating.**
+"""
+    )
+
+    last_used_custom = files("f5_tts").joinpath("infer/.cache/last_used_custom.txt")
+
+    def load_last_used_custom():
+        try:
+            with open(last_used_custom, "r") as f:
+                return f.read().split(",")
+        except FileNotFoundError:
+            last_used_custom.parent.mkdir(parents=True, exist_ok=True)
+            return [
+                "hf://SWivid/F5-TTS/F5TTS_Base/model_1200000.safetensors",
+                "hf://SWivid/F5-TTS/F5TTS_Base/vocab.txt",
+            ]
+
+    def switch_tts_model(new_choice):
+        global tts_model_choice
+        if new_choice == "Custom":  # override in case webpage is refreshed
+            custom_ckpt_path, custom_vocab_path = load_last_used_custom()
+            tts_model_choice = ["Custom", custom_ckpt_path, custom_vocab_path]
+            return gr.update(visible=True, value=custom_ckpt_path), gr.update(visible=True, value=custom_vocab_path)
+        else:
+            tts_model_choice = new_choice
+            return gr.update(visible=False), gr.update(visible=False)
+
+    def set_custom_model(custom_ckpt_path, custom_vocab_path):
+        global tts_model_choice
+        tts_model_choice = ["Custom", custom_ckpt_path, custom_vocab_path]
+        with open(last_used_custom, "w") as f:
+            f.write(f"{custom_ckpt_path},{custom_vocab_path}")
+
+    with gr.Row():
+        if not USING_SPACES:
+            choose_tts_model = gr.Radio(
+                choices=[DEFAULT_TTS_MODEL, "E2-TTS", "Custom"], label="Choose TTS Model", value=DEFAULT_TTS_MODEL
+            )
+        else:
+            choose_tts_model = gr.Radio(
+                choices=[DEFAULT_TTS_MODEL, "E2-TTS"], label="Choose TTS Model", value=DEFAULT_TTS_MODEL
+            )
+        custom_ckpt_path = gr.Dropdown(
+            choices=["hf://SWivid/F5-TTS/F5TTS_Base/model_1200000.safetensors"],
+            value=load_last_used_custom()[0],
+            allow_custom_value=True,
+            label="MODEL CKPT: local_path | hf://user_id/repo_id/model_ckpt",
+            visible=False,
+        )
+        custom_vocab_path = gr.Dropdown(
+            choices=["hf://SWivid/F5-TTS/F5TTS_Base/vocab.txt"],
+            value=load_last_used_custom()[1],
+            allow_custom_value=True,
+            label="VOCAB FILE: local_path | hf://user_id/repo_id/vocab_file",
+            visible=False,
+        )
+
+    choose_tts_model.change(
+        switch_tts_model,
+        inputs=[choose_tts_model],
+        outputs=[custom_ckpt_path, custom_vocab_path],
+        show_progress="hidden",
+    )
+    custom_ckpt_path.change(
+        set_custom_model,
+        inputs=[custom_ckpt_path, custom_vocab_path],
+        show_progress="hidden",
+    )
+    custom_vocab_path.change(
+        set_custom_model,
+        inputs=[custom_ckpt_path, custom_vocab_path],
+        show_progress="hidden",
+    )
+
+    gr.TabbedInterface(
+        [app_tts, app_multistyle, app_chat, app_credits],
+        ["Basic-TTS", "Multi-Speech", "Voice-Chat", "Credits"],
+    )
+
+
+@click.command()
+@click.option("--port", "-p", default=None, type=int, help="Port to run the app on")
+@click.option("--host", "-H", default=None, help="Host to run the app on")
+@click.option(
+    "--share",
+    "-s",
+    default=False,
+    is_flag=True,
+    help="Share the app via Gradio share link",
+)
+@click.option("--api", "-a", default=True, is_flag=True, help="Allow API access")
+def main(port, host, share, api):
+    global app
+    print("Starting app...")
+    app.queue(api_open=api).launch(server_name=host, server_port=port, share=share, show_api=api)
+
+
+if __name__ == "__main__":
+    if not USING_SPACES:
+        main()
+    else:
+        app.queue().launch()

ckpts/README.md

@@ -0,0 +1,10 @@
+
+Pretrained model ckpts. https://huggingface.co/SWivid/F5-TTS
+
+```
+ckpts/
+    E2TTS_Base/
+        model_1200000.pt
+    F5TTS_Base/
+        model_1200000.pt
+```

data/Emilia_ZH_EN_pinyin/vocab.txt

@@ -0,0 +1,2545 @@
+ 
+!
+"
+#
+$
+%
+&
+'
+(
+)
+*
++
+,
+-
+.
+/
+0
+1
+2
+3
+4
+5
+6
+7
+8
+9
+:
+;
+=
+>
+?
+@
+A
+B
+C
+D
+E
+F
+G
+H
+I
+J
+K
+L
+M
+N
+O
+P
+Q
+R
+S
+T
+U
+V
+W
+X
+Y
+Z
+[
+\
+]
+_
+a
+a1
+ai1
+ai2
+ai3
+ai4
+an1
+an3
+an4
+ang1
+ang2
+ang4
+ao1
+ao2
+ao3
+ao4
+b
+ba
+ba1
+ba2
+ba3
+ba4
+bai1
+bai2
+bai3
+bai4
+ban1
+ban2
+ban3
+ban4
+bang1
+bang2
+bang3
+bang4
+bao1
+bao2
+bao3
+bao4
+bei
+bei1
+bei2
+bei3
+bei4
+ben1
+ben2
+ben3
+ben4
+beng
+beng1
+beng2
+beng3
+beng4
+bi1
+bi2
+bi3
+bi4
+bian1
+bian2
+bian3
+bian4
+biao1
+biao2
+biao3
+bie1
+bie2
+bie3
+bie4
+bin1
+bin4
+bing1
+bing2
+bing3
+bing4
+bo
+bo1
+bo2
+bo3
+bo4
+bu2
+bu3
+bu4
+c
+ca1
+cai1
+cai2
+cai3
+cai4
+can1
+can2
+can3
+can4
+cang1
+cang2
+cao1
+cao2
+cao3
+ce4
+cen1
+cen2
+ceng1
+ceng2
+ceng4
+cha1
+cha2
+cha3
+cha4
+chai1
+chai2
+chan1
+chan2
+chan3
+chan4
+chang1
+chang2
+chang3
+chang4
+chao1
+chao2
+chao3
+che1
+che2
+che3
+che4
+chen1
+chen2
+chen3
+chen4
+cheng1
+cheng2
+cheng3
+cheng4
+chi1
+chi2
+chi3
+chi4
+chong1
+chong2
+chong3
+chong4
+chou1
+chou2
+chou3
+chou4
+chu1
+chu2
+chu3
+chu4
+chua1
+chuai1
+chuai2
+chuai3
+chuai4
+chuan1
+chuan2
+chuan3
+chuan4
+chuang1
+chuang2
+chuang3
+chuang4
+chui1
+chui2
+chun1
+chun2
+chun3
+chuo1
+chuo4
+ci1
+ci2
+ci3
+ci4
+cong1
+cong2
+cou4
+cu1
+cu4
+cuan1
+cuan2
+cuan4
+cui1
+cui3
+cui4
+cun1
+cun2
+cun4
+cuo1
+cuo2
+cuo4
+d
+da
+da1
+da2
+da3
+da4
+dai1
+dai2
+dai3
+dai4
+dan1
+dan2
+dan3
+dan4
+dang1
+dang2
+dang3
+dang4
+dao1
+dao2
+dao3
+dao4
+de
+de1
+de2
+dei3
+den4
+deng1
+deng2
+deng3
+deng4
+di1
+di2
+di3
+di4
+dia3
+dian1
+dian2
+dian3
+dian4
+diao1
+diao3
+diao4
+die1
+die2
+die4
+ding1
+ding2
+ding3
+ding4
+diu1
+dong1
+dong3
+dong4
+dou1
+dou2
+dou3
+dou4
+du1
+du2
+du3
+du4
+duan1
+duan2
+duan3
+duan4
+dui1
+dui4
+dun1
+dun3
+dun4
+duo1
+duo2
+duo3
+duo4
+e
+e1
+e2
+e3
+e4
+ei2
+en1
+en4
+er
+er2
+er3
+er4
+f
+fa1
+fa2
+fa3
+fa4
+fan1
+fan2
+fan3
+fan4
+fang1
+fang2
+fang3
+fang4
+fei1
+fei2
+fei3
+fei4
+fen1
+fen2
+fen3
+fen4
+feng1
+feng2
+feng3
+feng4
+fo2
+fou2
+fou3
+fu1
+fu2
+fu3
+fu4
+g
+ga1
+ga2
+ga3
+ga4
+gai1
+gai2
+gai3
+gai4
+gan1
+gan2
+gan3
+gan4
+gang1
+gang2
+gang3
+gang4
+gao1
+gao2
+gao3
+gao4
+ge1
+ge2
+ge3
+ge4
+gei2
+gei3
+gen1
+gen2
+gen3
+gen4
+geng1
+geng3
+geng4
+gong1
+gong3
+gong4
+gou1
+gou2
+gou3
+gou4
+gu
+gu1
+gu2
+gu3
+gu4
+gua1
+gua2
+gua3
+gua4
+guai1
+guai2
+guai3
+guai4
+guan1
+guan2
+guan3
+guan4
+guang1
+guang2
+guang3
+guang4
+gui1
+gui2
+gui3
+gui4
+gun3
+gun4
+guo1
+guo2
+guo3
+guo4
+h
+ha1
+ha2
+ha3
+hai1
+hai2
+hai3
+hai4
+han1
+han2
+han3
+han4
+hang1
+hang2
+hang4
+hao1
+hao2
+hao3
+hao4
+he1
+he2
+he4
+hei1
+hen2
+hen3
+hen4
+heng1
+heng2
+heng4
+hong1
+hong2
+hong3
+hong4
+hou1
+hou2
+hou3
+hou4
+hu1
+hu2
+hu3
+hu4
+hua1
+hua2
+hua4
+huai2
+huai4
+huan1
+huan2
+huan3
+huan4
+huang1
+huang2
+huang3
+huang4
+hui1
+hui2
+hui3
+hui4
+hun1
+hun2
+hun4
+huo
+huo1
+huo2
+huo3
+huo4
+i
+j
+ji1
+ji2
+ji3
+ji4
+jia
+jia1
+jia2
+jia3
+jia4
+jian1
+jian2
+jian3
+jian4
+jiang1
+jiang2
+jiang3
+jiang4
+jiao1
+jiao2
+jiao3
+jiao4
+jie1
+jie2
+jie3
+jie4
+jin1
+jin2
+jin3
+jin4
+jing1
+jing2
+jing3
+jing4
+jiong3
+jiu1
+jiu2
+jiu3
+jiu4
+ju1
+ju2
+ju3
+ju4
+juan1
+juan2
+juan3
+juan4
+jue1
+jue2
+jue4
+jun1
+jun4
+k
+ka1
+ka2
+ka3
+kai1
+kai2
+kai3
+kai4
+kan1
+kan2
+kan3
+kan4
+kang1
+kang2
+kang4
+kao1
+kao2
+kao3
+kao4
+ke1
+ke2
+ke3
+ke4
+ken3
+keng1
+kong1
+kong3
+kong4
+kou1
+kou2
+kou3
+kou4
+ku1
+ku2
+ku3
+ku4
+kua1
+kua3
+kua4
+kuai3
+kuai4
+kuan1
+kuan2
+kuan3
+kuang1
+kuang2
+kuang4
+kui1
+kui2
+kui3
+kui4
+kun1
+kun3
+kun4
+kuo4
+l
+la
+la1
+la2
+la3
+la4
+lai2
+lai4
+lan2
+lan3
+lan4
+lang1
+lang2
+lang3
+lang4
+lao1
+lao2
+lao3
+lao4
+le
+le1
+le4
+lei
+lei1
+lei2
+lei3
+lei4
+leng1
+leng2
+leng3
+leng4
+li
+li1
+li2
+li3
+li4
+lia3
+lian2
+lian3
+lian4
+liang2
+liang3
+liang4
+liao1
+liao2
+liao3
+liao4
+lie1
+lie2
+lie3
+lie4
+lin1
+lin2
+lin3
+lin4
+ling2
+ling3
+ling4
+liu1
+liu2
+liu3
+liu4
+long1
+long2
+long3
+long4
+lou1
+lou2
+lou3
+lou4
+lu1
+lu2
+lu3
+lu4
+luan2
+luan3
+luan4
+lun1
+lun2
+lun4
+luo1
+luo2
+luo3
+luo4
+lv2
+lv3
+lv4
+lve3
+lve4
+m
+ma
+ma1
+ma2
+ma3
+ma4
+mai2
+mai3
+mai4
+man1
+man2
+man3
+man4
+mang2
+mang3
+mao1
+mao2
+mao3
+mao4
+me
+mei2
+mei3
+mei4
+men
+men1
+men2
+men4
+meng
+meng1
+meng2
+meng3
+meng4
+mi1
+mi2
+mi3
+mi4
+mian2
+mian3
+mian4
+miao1
+miao2
+miao3
+miao4
+mie1
+mie4
+min2
+min3
+ming2
+ming3
+ming4
+miu4
+mo1
+mo2
+mo3
+mo4
+mou1
+mou2
+mou3
+mu2
+mu3
+mu4
+n
+n2
+na1
+na2
+na3
+na4
+nai2
+nai3
+nai4
+nan1
+nan2
+nan3
+nan4
+nang1
+nang2
+nang3
+nao1
+nao2
+nao3
+nao4
+ne
+ne2
+ne4
+nei3
+nei4
+nen4
+neng2
+ni1
+ni2
+ni3
+ni4
+nian1
+nian2
+nian3
+nian4
+niang2
+niang4
+niao2
+niao3
+niao4
+nie1
+nie4
+nin2
+ning2
+ning3
+ning4
+niu1
+niu2
+niu3
+niu4
+nong2
+nong4
+nou4
+nu2
+nu3
+nu4
+nuan3
+nuo2
+nuo4
+nv2
+nv3
+nve4
+o
+o1
+o2
+ou1
+ou2
+ou3
+ou4
+p
+pa1
+pa2
+pa4
+pai1
+pai2
+pai3
+pai4
+pan1
+pan2
+pan4
+pang1
+pang2
+pang4
+pao1
+pao2
+pao3
+pao4
+pei1
+pei2
+pei4
+pen1
+pen2
+pen4
+peng1
+peng2
+peng3
+peng4
+pi1
+pi2
+pi3
+pi4
+pian1
+pian2
+pian4
+piao1
+piao2
+piao3
+piao4
+pie1
+pie2
+pie3
+pin1
+pin2
+pin3
+pin4
+ping1
+ping2
+po1
+po2
+po3
+po4
+pou1
+pu1
+pu2
+pu3
+pu4
+q
+qi1
+qi2
+qi3
+qi4
+qia1
+qia3
+qia4
+qian1
+qian2
+qian3
+qian4
+qiang1
+qiang2
+qiang3
+qiang4
+qiao1
+qiao2
+qiao3
+qiao4
+qie1
+qie2
+qie3
+qie4
+qin1
+qin2
+qin3
+qin4
+qing1
+qing2
+qing3
+qing4
+qiong1
+qiong2
+qiu1
+qiu2
+qiu3
+qu1
+qu2
+qu3
+qu4
+quan1
+quan2
+quan3
+quan4
+que1
+que2
+que4
+qun2
+r
+ran2
+ran3
+rang1
+rang2
+rang3
+rang4
+rao2
+rao3
+rao4
+re2
+re3
+re4
+ren2
+ren3
+ren4
+reng1
+reng2
+ri4
+rong1
+rong2
+rong3
+rou2
+rou4
+ru2
+ru3
+ru4
+ruan2
+ruan3
+rui3
+rui4
+run4
+ruo4
+s
+sa1
+sa2
+sa3
+sa4
+sai1
+sai4
+san1
+san2
+san3
+san4
+sang1
+sang3
+sang4
+sao1
+sao2
+sao3
+sao4
+se4
+sen1
+seng1
+sha1
+sha2
+sha3
+sha4
+shai1
+shai2
+shai3
+shai4
+shan1
+shan3
+shan4
+shang
+shang1
+shang3
+shang4
+shao1
+shao2
+shao3
+shao4
+she1
+she2
+she3
+she4
+shei2
+shen1
+shen2
+shen3
+shen4
+sheng1
+sheng2
+sheng3
+sheng4
+shi
+shi1
+shi2
+shi3
+shi4
+shou1
+shou2
+shou3
+shou4
+shu1
+shu2
+shu3
+shu4
+shua1
+shua2
+shua3
+shua4
+shuai1
+shuai3
+shuai4
+shuan1
+shuan4
+shuang1
+shuang3
+shui2
+shui3
+shui4
+shun3
+shun4
+shuo1
+shuo4
+si1
+si2
+si3
+si4
+song1
+song3
+song4
+sou1
+sou3
+sou4
+su1
+su2
+su4
+suan1
+suan4
+sui1
+sui2
+sui3
+sui4
+sun1
+sun3
+suo
+suo1
+suo2
+suo3
+t
+ta1
+ta2
+ta3
+ta4
+tai1
+tai2
+tai4
+tan1
+tan2
+tan3
+tan4
+tang1
+tang2
+tang3
+tang4
+tao1
+tao2
+tao3
+tao4
+te4
+teng2
+ti1
+ti2
+ti3
+ti4
+tian1
+tian2
+tian3
+tiao1
+tiao2
+tiao3
+tiao4
+tie1
+tie2
+tie3
+tie4
+ting1
+ting2
+ting3
+tong1
+tong2
+tong3
+tong4
+tou
+tou1
+tou2
+tou4
+tu1
+tu2
+tu3
+tu4
+tuan1
+tuan2
+tui1
+tui2
+tui3
+tui4
+tun1
+tun2
+tun4
+tuo1
+tuo2
+tuo3
+tuo4
+u
+v
+w
+wa
+wa1
+wa2
+wa3
+wa4
+wai1
+wai3
+wai4
+wan1
+wan2
+wan3
+wan4
+wang1
+wang2
+wang3
+wang4
+wei1
+wei2
+wei3
+wei4
+wen1
+wen2
+wen3
+wen4
+weng1
+weng4
+wo1
+wo2
+wo3
+wo4
+wu1
+wu2
+wu3
+wu4
+x
+xi1
+xi2
+xi3
+xi4
+xia1
+xia2
+xia4
+xian1
+xian2
+xian3
+xian4
+xiang1
+xiang2
+xiang3
+xiang4
+xiao1
+xiao2
+xiao3
+xiao4
+xie1
+xie2
+xie3
+xie4
+xin1
+xin2
+xin4
+xing1
+xing2
+xing3
+xing4
+xiong1
+xiong2
+xiu1
+xiu3
+xiu4
+xu
+xu1
+xu2
+xu3
+xu4
+xuan1
+xuan2
+xuan3
+xuan4
+xue1
+xue2
+xue3
+xue4
+xun1
+xun2
+xun4
+y
+ya
+ya1
+ya2
+ya3
+ya4
+yan1
+yan2
+yan3
+yan4
+yang1
+yang2
+yang3
+yang4
+yao1
+yao2
+yao3
+yao4
+ye1
+ye2
+ye3
+ye4
+yi
+yi1
+yi2
+yi3
+yi4
+yin1
+yin2
+yin3
+yin4
+ying1
+ying2
+ying3
+ying4
+yo1
+yong1
+yong2
+yong3
+yong4
+you1
+you2
+you3
+you4
+yu1
+yu2
+yu3
+yu4
+yuan1
+yuan2
+yuan3
+yuan4
+yue1
+yue4
+yun1
+yun2
+yun3
+yun4
+z
+za1
+za2
+za3
+zai1
+zai3
+zai4
+zan1
+zan2
+zan3
+zan4
+zang1
+zang4
+zao1
+zao2
+zao3
+zao4
+ze2
+ze4
+zei2
+zen3
+zeng1
+zeng4
+zha1
+zha2
+zha3
+zha4
+zhai1
+zhai2
+zhai3
+zhai4
+zhan1
+zhan2
+zhan3
+zhan4
+zhang1
+zhang2
+zhang3
+zhang4
+zhao1
+zhao2
+zhao3
+zhao4
+zhe
+zhe1
+zhe2
+zhe3
+zhe4
+zhen1
+zhen2
+zhen3
+zhen4
+zheng1
+zheng2
+zheng3
+zheng4
+zhi1
+zhi2
+zhi3
+zhi4
+zhong1
+zhong2
+zhong3
+zhong4
+zhou1
+zhou2
+zhou3
+zhou4
+zhu1
+zhu2
+zhu3
+zhu4
+zhua1
+zhua2
+zhua3
+zhuai1
+zhuai3
+zhuai4
+zhuan1
+zhuan2
+zhuan3
+zhuan4
+zhuang1
+zhuang4
+zhui1
+zhui4
+zhun1
+zhun2
+zhun3
+zhuo1
+zhuo2
+zi
+zi1
+zi2
+zi3
+zi4
+zong1
+zong2
+zong3
+zong4
+zou1
+zou2
+zou3
+zou4
+zu1
+zu2
+zu3
+zuan1
+zuan3
+zuan4
+zui2
+zui3
+zui4
+zun1
+zuo
+zuo1
+zuo2
+zuo3
+zuo4
+{
+~
+¡
+¢
+£
+¥
+§
+¨
+©
+«
+®
+¯
+°
+±
+²
+³
+´
+µ
+·
+¹
+º
+»
+¼
+½
+¾
+¿
+À
+Á
+Â
+Ã
+Ä
+Å
+Æ
+Ç
+È
+É
+Ê
+Í
+Î
+Ñ
+Ó
+Ö
+×
+Ø
+Ú
+Ü
+Ý
+Þ
+ß
+à
+á
+â
+ã
+ä
+å
+æ
+ç
+è
+é
+ê
+ë
+ì
+í
+î
+ï
+ð
+ñ
+ò
+ó
+ô
+õ
+ö
+ø
+ù
+ú
+û
+ü
+ý
+Ā
+ā
+ă
+ą
+ć
+Č
+č
+Đ
+đ
+ē
+ė
+ę
+ě
+ĝ
+ğ
+ħ
+ī
+į
+İ
+ı
+Ł
+ł
+ń
+ņ
+ň
+ŋ
+Ō
+ō
+ő
+œ
+ř
+Ś
+ś
+Ş
+ş
+Š
+š
+Ť
+ť
+ũ
+ū
+ź
+Ż
+ż
+Ž
+ž
+ơ
+ư
+ǎ
+ǐ
+ǒ
+ǔ
+ǚ
+ș
+ț
+ɑ
+ɔ
+ɕ
+ə
+ɛ
+ɜ
+ɡ
+ɣ
+ɪ
+ɫ
+ɴ
+ɹ
+ɾ
+ʃ
+ʊ
+ʌ
+ʒ
+ʔ
+ʰ
+ʷ
+ʻ
+ʾ
+ʿ
+ˈ
+ː
+˙
+˜
+ˢ
+́
+̅
+Α
+Β
+Δ
+Ε
+Θ
+Κ
+Λ
+Μ
+Ξ
+Π
+Σ
+Τ
+Φ
+Χ
+Ψ
+Ω
+ά
+έ
+ή
+ί
+α
+β
+γ
+δ
+ε
+ζ
+η
+θ
+ι
+κ
+λ
+μ
+ν
+ξ
+ο
+π
+ρ
+ς
+σ
+τ
+υ
+φ
+χ
+ψ
+ω
+ϊ
+ό
+ύ
+ώ
+ϕ
+ϵ
+Ё
+А
+Б
+В
+Г
+Д
+Е
+Ж
+З
+И
+Й
+К
+Л
+М
+Н
+О
+П
+Р
+С
+Т
+У
+Ф
+Х
+Ц
+Ч
+Ш
+Щ
+Ы
+Ь
+Э
+Ю
+Я
+а
+б
+в
+г
+д
+е
+ж
+з
+и
+й
+к
+л
+м
+н
+о
+п
+р
+с
+т
+у
+ф
+х
+ц
+ч
+ш
+щ
+ъ
+ы
+ь
+э
+ю
+я
+ё
+і
+ְ
+ִ
+ֵ
+ֶ
+ַ
+ָ
+ֹ
+ּ
+־
+ׁ
+א
+ב
+ג
+ד
+ה
+ו
+ז
+ח
+ט
+י
+כ
+ל
+ם
+מ
+ן
+נ
+ס
+ע
+פ
+ק
+ר
+ש
+ת
+أ
+ب
+ة
+ت
+ج
+ح
+د
+ر
+ز
+س
+ص
+ط
+ع
+ق
+ك
+ل
+م
+ن
+ه
+و
+ي
+َ
+ُ
+ِ
+ْ
+ก
+ข
+ง
+จ
+ต
+ท
+น
+ป
+ย
+ร
+ว
+ส
+ห
+อ
+ฮ
+ั
+า
+ี
+ึ
+โ
+ใ
+ไ
+่
+้
+์
+ḍ
+Ḥ
+ḥ
+ṁ
+ṃ
+ṅ
+ṇ
+Ṛ
+ṛ
+Ṣ
+ṣ
+Ṭ
+ṭ
+ạ
+ả
+Ấ
+ấ
+ầ
+ậ
+ắ
+ằ
+ẻ
+ẽ
+ế
+ề
+ể
+ễ
+ệ
+ị
+ọ
+ỏ
+ố
+ồ
+ộ
+ớ
+ờ
+ở
+ụ
+ủ
+ứ
+ữ
+ἀ
+ἁ
+Ἀ
+ἐ
+ἔ
+ἰ
+ἱ
+ὀ
+ὁ
+ὐ
+ὲ
+ὸ
+ᾶ
+᾽
+ῆ
+ῇ
+ῶ
+‎
+‑
+‒
+–
+—
+―
+‖
+†
+‡
+•
+…
+‧
+‬
+′
+″
+⁄
+⁡
+⁰
+⁴
+⁵
+⁶
+⁷
+⁸
+⁹
+₁
+₂
+₃
+€
+₱
+₹
+₽
+℃
+ℏ
+ℓ
+№
+ℝ
+™
+⅓
+⅔
+⅛
+→
+∂
+∈
+∑
+−
+∗
+√
+∞
+∫
+≈
+≠
+≡
+≤
+≥
+⋅
+⋯
+█
+♪
+⟨
+⟩
+、
+。
+《
+》
+「
+」
+【
+】
+あ
+う
+え
+お
+か
+が
+き
+ぎ
+く
+ぐ
+け
+げ
+こ
+ご
+さ
+し
+じ
+す
+ず
+せ
+ぜ
+そ
+ぞ
+た
+だ
+ち
+っ
+つ
+で
+と
+ど
+な
+に
+ね
+の
+は
+ば
+ひ
+ぶ
+へ
+べ
+ま
+み
+む
+め
+も
+ゃ
+や
+ゆ
+ょ
+よ
+ら
+り
+る
+れ
+ろ
+わ
+を
+ん
+ァ
+ア
+ィ
+イ
+ウ
+ェ
+エ
+オ
+カ
+ガ
+キ
+ク
+ケ
+ゲ
+コ
+ゴ
+サ
+ザ
+シ
+ジ
+ス
+ズ
+セ
+ゾ
+タ
+ダ
+チ
+ッ
+ツ
+テ
+デ
+ト
+ド
+ナ
+ニ
+ネ
+ノ
+バ
+パ
+ビ
+ピ
+フ
+プ
+ヘ
+ベ
+ペ
+ホ
+ボ
+ポ
+マ
+ミ
+ム
+メ
+モ
+ャ
+ヤ
+ュ
+ユ
+ョ
+ヨ
+ラ
+リ
+ル
+レ
+ロ
+ワ
+ン
+・
+ー
+ㄋ
+ㄍ
+ㄎ
+ㄏ
+ㄓ
+ㄕ
+ㄚ
+ㄜ
+ㄟ
+ㄤ
+ㄥ
+ㄧ
+ㄱ
+ㄴ
+ㄷ
+ㄹ
+ㅁ
+ㅂ
+ㅅ
+ㅈ
+ㅍ
+ㅎ
+ㅏ
+ㅓ
+ㅗ
+ㅜ
+ㅡ
+ㅣ
+㗎
+가
+각
+간
+갈
+감
+갑
+갓
+갔
+강
+같
+개
+거
+건
+걸
+겁
+것
+겉
+게
+겠
+겨
+결
+겼
+경
+계
+고
+곤
+골
+곱
+공
+과
+관
+광
+교
+구
+국
+굴
+귀
+귄
+그
+근
+글
+금
+기
+긴
+길
+까
+깍
+깔
+깜
+깨
+께
+꼬
+꼭
+꽃
+꾸
+꿔
+끔
+끗
+끝
+끼
+나
+난
+날
+남
+납
+내
+냐
+냥
+너
+넘
+넣
+네
+녁
+년
+녕
+노
+녹
+놀
+누
+눈
+느
+는
+늘
+니
+님
+닙
+다
+닥
+단
+달
+닭
+당
+대
+더
+덕
+던
+덥
+데
+도
+독
+동
+돼
+됐
+되
+된
+될
+두
+둑
+둥
+드
+들
+등
+디
+따
+딱
+딸
+땅
+때
+떤
+떨
+떻
+또
+똑
+뚱
+뛰
+뜻
+띠
+라
+락
+란
+람
+랍
+랑
+래
+랜
+러
+런
+럼
+렇
+레
+려
+력
+렵
+렸
+로
+록
+롬
+루
+르
+른
+를
+름
+릉
+리
+릴
+림
+마
+막
+만
+많
+말
+맑
+맙
+맛
+매
+머
+먹
+멍
+메
+면
+명
+몇
+모
+목
+몸
+못
+무
+문
+물
+뭐
+뭘
+미
+민
+밌
+밑
+바
+박
+밖
+반
+받
+발
+밤
+밥
+방
+배
+백
+밸
+뱀
+버
+번
+벌
+벚
+베
+벼
+벽
+별
+병
+보
+복
+본
+볼
+봐
+봤
+부
+분
+불
+비
+빔
+빛
+빠
+빨
+뼈
+뽀
+뿅
+쁘
+사
+산
+살
+삼
+샀
+상
+새
+색
+생
+서
+선
+설
+섭
+섰
+성
+세
+셔
+션
+셨
+소
+속
+손
+송
+수
+숙
+순
+술
+숫
+숭
+숲
+쉬
+쉽
+스
+슨
+습
+슷
+시
+식
+신
+실
+싫
+심
+십
+싶
+싸
+써
+쓰
+쓴
+씌
+씨
+씩
+씬
+아
+악
+안
+않
+알
+야
+약
+얀
+양
+얘
+어
+언
+얼
+엄
+업
+없
+었
+엉
+에
+여
+역
+연
+염
+엽
+영
+옆
+예
+옛
+오
+온
+올
+옷
+옹
+와
+왔
+왜
+요
+욕
+용
+우
+운
+울
+웃
+워
+원
+월
+웠
+위
+윙
+유
+육
+윤
+으
+은
+을
+음
+응
+의
+이
+익
+인
+일
+읽
+임
+입
+있
+자
+작
+잔
+잖
+잘
+잡
+잤
+장
+재
+저
+전
+점
+정
+제
+져
+졌
+조
+족
+좀
+종
+좋
+죠
+주
+준
+줄
+중
+줘
+즈
+즐
+즘
+지
+진
+집
+짜
+짝
+쩌
+쪼
+쪽
+쫌
+쭈
+쯔
+찌
+찍
+차
+착
+찾
+책
+처
+천
+철
+체
+쳐
+쳤
+초
+촌
+추
+출
+춤
+춥
+춰
+치
+친
+칠
+침
+칩
+칼
+커
+켓
+코
+콩
+쿠
+퀴
+크
+큰
+큽
+키
+킨
+타
+태
+터
+턴
+털
+테
+토
+통
+투
+트
+특
+튼
+틀
+티
+팀
+파
+팔
+패
+페
+펜
+펭
+평
+포
+폭
+표
+품
+풍
+프
+플
+피
+필
+하
+학
+한
+할
+함
+합
+항
+해
+햇
+했
+행
+허
+험
+형
+혜
+호
+혼
+홀
+화
+회
+획
+후
+휴
+흐
+흔
+희
+히
+힘
+ﷺ
+ﷻ
+！
+，
+？
+�
+𠮶

env/bin/Activate.ps1

@@ -0,0 +1,247 @@
+<#
+.Synopsis
+Activate a Python virtual environment for the current PowerShell session.
+
+.Description
+Pushes the python executable for a virtual environment to the front of the
+$Env:PATH environment variable and sets the prompt to signify that you are
+in a Python virtual environment. Makes use of the command line switches as
+well as the `pyvenv.cfg` file values present in the virtual environment.
+
+.Parameter VenvDir
+Path to the directory that contains the virtual environment to activate. The
+default value for this is the parent of the directory that the Activate.ps1
+script is located within.
+
+.Parameter Prompt
+The prompt prefix to display when this virtual environment is activated. By
+default, this prompt is the name of the virtual environment folder (VenvDir)
+surrounded by parentheses and followed by a single space (ie. '(.venv) ').
+
+.Example
+Activate.ps1
+Activates the Python virtual environment that contains the Activate.ps1 script.
+
+.Example
+Activate.ps1 -Verbose
+Activates the Python virtual environment that contains the Activate.ps1 script,
+and shows extra information about the activation as it executes.
+
+.Example
+Activate.ps1 -VenvDir C:\Users\MyUser\Common\.venv
+Activates the Python virtual environment located in the specified location.
+
+.Example
+Activate.ps1 -Prompt "MyPython"
+Activates the Python virtual environment that contains the Activate.ps1 script,
+and prefixes the current prompt with the specified string (surrounded in
+parentheses) while the virtual environment is active.
+
+.Notes
+On Windows, it may be required to enable this Activate.ps1 script by setting the
+execution policy for the user. You can do this by issuing the following PowerShell
+command:
+
+PS C:\> Set-ExecutionPolicy -ExecutionPolicy RemoteSigned -Scope CurrentUser
+
+For more information on Execution Policies: 
+https://go.microsoft.com/fwlink/?LinkID=135170
+
+#>
+Param(
+    [Parameter(Mandatory = $false)]
+    [String]
+    $VenvDir,
+    [Parameter(Mandatory = $false)]
+    [String]
+    $Prompt
+)
+
+<# Function declarations --------------------------------------------------- #>
+
+<#
+.Synopsis
+Remove all shell session elements added by the Activate script, including the
+addition of the virtual environment's Python executable from the beginning of
+the PATH variable.
+
+.Parameter NonDestructive
+If present, do not remove this function from the global namespace for the
+session.
+
+#>
+function global:deactivate ([switch]$NonDestructive) {
+    # Revert to original values
+
+    # The prior prompt:
+    if (Test-Path -Path Function:_OLD_VIRTUAL_PROMPT) {
+        Copy-Item -Path Function:_OLD_VIRTUAL_PROMPT -Destination Function:prompt
+        Remove-Item -Path Function:_OLD_VIRTUAL_PROMPT
+    }
+
+    # The prior PYTHONHOME:
+    if (Test-Path -Path Env:_OLD_VIRTUAL_PYTHONHOME) {
+        Copy-Item -Path Env:_OLD_VIRTUAL_PYTHONHOME -Destination Env:PYTHONHOME
+        Remove-Item -Path Env:_OLD_VIRTUAL_PYTHONHOME
+    }
+
+    # The prior PATH:
+    if (Test-Path -Path Env:_OLD_VIRTUAL_PATH) {
+        Copy-Item -Path Env:_OLD_VIRTUAL_PATH -Destination Env:PATH
+        Remove-Item -Path Env:_OLD_VIRTUAL_PATH
+    }
+
+    # Just remove the VIRTUAL_ENV altogether:
+    if (Test-Path -Path Env:VIRTUAL_ENV) {
+        Remove-Item -Path env:VIRTUAL_ENV
+    }
+
+    # Just remove VIRTUAL_ENV_PROMPT altogether.
+    if (Test-Path -Path Env:VIRTUAL_ENV_PROMPT) {
+        Remove-Item -Path env:VIRTUAL_ENV_PROMPT
+    }
+
+    # Just remove the _PYTHON_VENV_PROMPT_PREFIX altogether:
+    if (Get-Variable -Name "_PYTHON_VENV_PROMPT_PREFIX" -ErrorAction SilentlyContinue) {
+        Remove-Variable -Name _PYTHON_VENV_PROMPT_PREFIX -Scope Global -Force
+    }
+
+    # Leave deactivate function in the global namespace if requested:
+    if (-not $NonDestructive) {
+        Remove-Item -Path function:deactivate
+    }
+}
+
+<#
+.Description
+Get-PyVenvConfig parses the values from the pyvenv.cfg file located in the
+given folder, and returns them in a map.
+
+For each line in the pyvenv.cfg file, if that line can be parsed into exactly
+two strings separated by `=` (with any amount of whitespace surrounding the =)
+then it is considered a `key = value` line. The left hand string is the key,
+the right hand is the value.
+
+If the value starts with a `'` or a `"` then the first and last character is
+stripped from the value before being captured.
+
+.Parameter ConfigDir
+Path to the directory that contains the `pyvenv.cfg` file.
+#>
+function Get-PyVenvConfig(
+    [String]
+    $ConfigDir
+) {
+    Write-Verbose "Given ConfigDir=$ConfigDir, obtain values in pyvenv.cfg"
+
+    # Ensure the file exists, and issue a warning if it doesn't (but still allow the function to continue).
+    $pyvenvConfigPath = Join-Path -Resolve -Path $ConfigDir -ChildPath 'pyvenv.cfg' -ErrorAction Continue
+
+    # An empty map will be returned if no config file is found.
+    $pyvenvConfig = @{ }
+
+    if ($pyvenvConfigPath) {
+
+        Write-Verbose "File exists, parse `key = value` lines"
+        $pyvenvConfigContent = Get-Content -Path $pyvenvConfigPath
+
+        $pyvenvConfigContent | ForEach-Object {
+            $keyval = $PSItem -split "\s*=\s*", 2
+            if ($keyval[0] -and $keyval[1]) {
+                $val = $keyval[1]
+
+                # Remove extraneous quotations around a string value.
+                if ("'""".Contains($val.Substring(0, 1))) {
+                    $val = $val.Substring(1, $val.Length - 2)
+                }
+
+                $pyvenvConfig[$keyval[0]] = $val
+                Write-Verbose "Adding Key: '$($keyval[0])'='$val'"
+            }
+        }
+    }
+    return $pyvenvConfig
+}
+
+
+<# Begin Activate script --------------------------------------------------- #>
+
+# Determine the containing directory of this script
+$VenvExecPath = Split-Path -Parent $MyInvocation.MyCommand.Definition
+$VenvExecDir = Get-Item -Path $VenvExecPath
+
+Write-Verbose "Activation script is located in path: '$VenvExecPath'"
+Write-Verbose "VenvExecDir Fullname: '$($VenvExecDir.FullName)"
+Write-Verbose "VenvExecDir Name: '$($VenvExecDir.Name)"
+
+# Set values required in priority: CmdLine, ConfigFile, Default
+# First, get the location of the virtual environment, it might not be
+# VenvExecDir if specified on the command line.
+if ($VenvDir) {
+    Write-Verbose "VenvDir given as parameter, using '$VenvDir' to determine values"
+}
+else {
+    Write-Verbose "VenvDir not given as a parameter, using parent directory name as VenvDir."
+    $VenvDir = $VenvExecDir.Parent.FullName.TrimEnd("\\/")
+    Write-Verbose "VenvDir=$VenvDir"
+}
+
+# Next, read the `pyvenv.cfg` file to determine any required value such
+# as `prompt`.
+$pyvenvCfg = Get-PyVenvConfig -ConfigDir $VenvDir
+
+# Next, set the prompt from the command line, or the config file, or
+# just use the name of the virtual environment folder.
+if ($Prompt) {
+    Write-Verbose "Prompt specified as argument, using '$Prompt'"
+}
+else {
+    Write-Verbose "Prompt not specified as argument to script, checking pyvenv.cfg value"
+    if ($pyvenvCfg -and $pyvenvCfg['prompt']) {
+        Write-Verbose "  Setting based on value in pyvenv.cfg='$($pyvenvCfg['prompt'])'"
+        $Prompt = $pyvenvCfg['prompt'];
+    }
+    else {
+        Write-Verbose "  Setting prompt based on parent's directory's name. (Is the directory name passed to venv module when creating the virtual environment)"
+        Write-Verbose "  Got leaf-name of $VenvDir='$(Split-Path -Path $venvDir -Leaf)'"
+        $Prompt = Split-Path -Path $venvDir -Leaf
+    }
+}
+
+Write-Verbose "Prompt = '$Prompt'"
+Write-Verbose "VenvDir='$VenvDir'"
+
+# Deactivate any currently active virtual environment, but leave the
+# deactivate function in place.
+deactivate -nondestructive
+
+# Now set the environment variable VIRTUAL_ENV, used by many tools to determine
+# that there is an activated venv.
+$env:VIRTUAL_ENV = $VenvDir
+
+if (-not $Env:VIRTUAL_ENV_DISABLE_PROMPT) {
+
+    Write-Verbose "Setting prompt to '$Prompt'"
+
+    # Set the prompt to include the env name
+    # Make sure _OLD_VIRTUAL_PROMPT is global
+    function global:_OLD_VIRTUAL_PROMPT { "" }
+    Copy-Item -Path function:prompt -Destination function:_OLD_VIRTUAL_PROMPT
+    New-Variable -Name _PYTHON_VENV_PROMPT_PREFIX -Description "Python virtual environment prompt prefix" -Scope Global -Option ReadOnly -Visibility Public -Value $Prompt
+
+    function global:prompt {
+        Write-Host -NoNewline -ForegroundColor Green "($_PYTHON_VENV_PROMPT_PREFIX) "
+        _OLD_VIRTUAL_PROMPT
+    }
+    $env:VIRTUAL_ENV_PROMPT = $Prompt
+}
+
+# Clear PYTHONHOME
+if (Test-Path -Path Env:PYTHONHOME) {
+    Copy-Item -Path Env:PYTHONHOME -Destination Env:_OLD_VIRTUAL_PYTHONHOME
+    Remove-Item -Path Env:PYTHONHOME
+}
+
+# Add the venv to the PATH
+Copy-Item -Path Env:PATH -Destination Env:_OLD_VIRTUAL_PATH
+$Env:PATH = "$VenvExecDir$([System.IO.Path]::PathSeparator)$Env:PATH"

env/bin/accelerate

@@ -0,0 +1,8 @@
+#!/var/www/html/hugging_setup/E2-F5-TTS/env/bin/python3
+# -*- coding: utf-8 -*-
+import re
+import sys
+from accelerate.commands.accelerate_cli import main
+if __name__ == '__main__':
+    sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
+    sys.exit(main())

env/bin/accelerate-config

@@ -0,0 +1,8 @@
+#!/var/www/html/hugging_setup/E2-F5-TTS/env/bin/python3
+# -*- coding: utf-8 -*-
+import re
+import sys
+from accelerate.commands.config import main
+if __name__ == '__main__':
+    sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
+    sys.exit(main())

env/bin/accelerate-estimate-memory

@@ -0,0 +1,8 @@
+#!/var/www/html/hugging_setup/E2-F5-TTS/env/bin/python3
+# -*- coding: utf-8 -*-
+import re
+import sys
+from accelerate.commands.estimate import main
+if __name__ == '__main__':
+    sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
+    sys.exit(main())

env/bin/accelerate-launch

@@ -0,0 +1,8 @@
+#!/var/www/html/hugging_setup/E2-F5-TTS/env/bin/python3
+# -*- coding: utf-8 -*-
+import re
+import sys
+from accelerate.commands.launch import main
+if __name__ == '__main__':
+    sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
+    sys.exit(main())

env/bin/accelerate-merge-weights

@@ -0,0 +1,8 @@
+#!/var/www/html/hugging_setup/E2-F5-TTS/env/bin/python3
+# -*- coding: utf-8 -*-
+import re
+import sys
+from accelerate.commands.merge import main
+if __name__ == '__main__':
+    sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
+    sys.exit(main())

env/bin/activate

@@ -0,0 +1,70 @@
+# This file must be used with "source bin/activate" *from bash*
+# You cannot run it directly
+
+deactivate () {
+    # reset old environment variables
+    if [ -n "${_OLD_VIRTUAL_PATH:-}" ] ; then
+        PATH="${_OLD_VIRTUAL_PATH:-}"
+        export PATH
+        unset _OLD_VIRTUAL_PATH
+    fi
+    if [ -n "${_OLD_VIRTUAL_PYTHONHOME:-}" ] ; then
+        PYTHONHOME="${_OLD_VIRTUAL_PYTHONHOME:-}"
+        export PYTHONHOME
+        unset _OLD_VIRTUAL_PYTHONHOME
+    fi
+
+    # Call hash to forget past commands. Without forgetting
+    # past commands the $PATH changes we made may not be respected
+    hash -r 2> /dev/null
+
+    if [ -n "${_OLD_VIRTUAL_PS1:-}" ] ; then
+        PS1="${_OLD_VIRTUAL_PS1:-}"
+        export PS1
+        unset _OLD_VIRTUAL_PS1
+    fi
+
+    unset VIRTUAL_ENV
+    unset VIRTUAL_ENV_PROMPT
+    if [ ! "${1:-}" = "nondestructive" ] ; then
+    # Self destruct!
+        unset -f deactivate
+    fi
+}
+
+# unset irrelevant variables
+deactivate nondestructive
+
+# on Windows, a path can contain colons and backslashes and has to be converted:
+if [ "${OSTYPE:-}" = "cygwin" ] || [ "${OSTYPE:-}" = "msys" ] ; then
+    # transform D:\path\to\venv to /d/path/to/venv on MSYS
+    # and to /cygdrive/d/path/to/venv on Cygwin
+    export VIRTUAL_ENV=$(cygpath "/var/www/html/hugging_setup/E2-F5-TTS/env")
+else
+    # use the path as-is
+    export VIRTUAL_ENV="/var/www/html/hugging_setup/E2-F5-TTS/env"
+fi
+
+_OLD_VIRTUAL_PATH="$PATH"
+PATH="$VIRTUAL_ENV/bin:$PATH"
+export PATH
+
+# unset PYTHONHOME if set
+# this will fail if PYTHONHOME is set to the empty string (which is bad anyway)
+# could use `if (set -u; : $PYTHONHOME) ;` in bash
+if [ -n "${PYTHONHOME:-}" ] ; then
+    _OLD_VIRTUAL_PYTHONHOME="${PYTHONHOME:-}"
+    unset PYTHONHOME
+fi
+
+if [ -z "${VIRTUAL_ENV_DISABLE_PROMPT:-}" ] ; then
+    _OLD_VIRTUAL_PS1="${PS1:-}"
+    PS1="(env) ${PS1:-}"
+    export PS1
+    VIRTUAL_ENV_PROMPT="(env) "
+    export VIRTUAL_ENV_PROMPT
+fi
+
+# Call hash to forget past commands. Without forgetting
+# past commands the $PATH changes we made may not be respected
+hash -r 2> /dev/null

env/bin/activate.csh

@@ -0,0 +1,27 @@
+# This file must be used with "source bin/activate.csh" *from csh*.
+# You cannot run it directly.
+
+# Created by Davide Di Blasi <[email protected]>.
+# Ported to Python 3.3 venv by Andrew Svetlov <[email protected]>
+
+alias deactivate 'test $?_OLD_VIRTUAL_PATH != 0 && setenv PATH "$_OLD_VIRTUAL_PATH" && unset _OLD_VIRTUAL_PATH; rehash; test $?_OLD_VIRTUAL_PROMPT != 0 && set prompt="$_OLD_VIRTUAL_PROMPT" && unset _OLD_VIRTUAL_PROMPT; unsetenv VIRTUAL_ENV; unsetenv VIRTUAL_ENV_PROMPT; test "\!:*" != "nondestructive" && unalias deactivate'
+
+# Unset irrelevant variables.
+deactivate nondestructive
+
+setenv VIRTUAL_ENV "/var/www/html/hugging_setup/E2-F5-TTS/env"
+
+set _OLD_VIRTUAL_PATH="$PATH"
+setenv PATH "$VIRTUAL_ENV/bin:$PATH"
+
+
+set _OLD_VIRTUAL_PROMPT="$prompt"
+
+if (! "$?VIRTUAL_ENV_DISABLE_PROMPT") then
+    set prompt = "(env) $prompt"
+    setenv VIRTUAL_ENV_PROMPT "(env) "
+endif
+
+alias pydoc python -m pydoc
+
+rehash

env/bin/activate.fish

@@ -0,0 +1,69 @@
+# This file must be used with "source <venv>/bin/activate.fish" *from fish*
+# (https://fishshell.com/). You cannot run it directly.
+
+function deactivate  -d "Exit virtual environment and return to normal shell environment"
+    # reset old environment variables
+    if test -n "$_OLD_VIRTUAL_PATH"
+        set -gx PATH $_OLD_VIRTUAL_PATH
+        set -e _OLD_VIRTUAL_PATH
+    end
+    if test -n "$_OLD_VIRTUAL_PYTHONHOME"
+        set -gx PYTHONHOME $_OLD_VIRTUAL_PYTHONHOME
+        set -e _OLD_VIRTUAL_PYTHONHOME
+    end
+
+    if test -n "$_OLD_FISH_PROMPT_OVERRIDE"
+        set -e _OLD_FISH_PROMPT_OVERRIDE
+        # prevents error when using nested fish instances (Issue #93858)
+        if functions -q _old_fish_prompt
+            functions -e fish_prompt
+            functions -c _old_fish_prompt fish_prompt
+            functions -e _old_fish_prompt
+        end
+    end
+
+    set -e VIRTUAL_ENV
+    set -e VIRTUAL_ENV_PROMPT
+    if test "$argv[1]" != "nondestructive"
+        # Self-destruct!
+        functions -e deactivate
+    end
+end
+
+# Unset irrelevant variables.
+deactivate nondestructive
+
+set -gx VIRTUAL_ENV "/var/www/html/hugging_setup/E2-F5-TTS/env"
+
+set -gx _OLD_VIRTUAL_PATH $PATH
+set -gx PATH "$VIRTUAL_ENV/bin" $PATH
+
+# Unset PYTHONHOME if set.
+if set -q PYTHONHOME
+    set -gx _OLD_VIRTUAL_PYTHONHOME $PYTHONHOME
+    set -e PYTHONHOME
+end
+
+if test -z "$VIRTUAL_ENV_DISABLE_PROMPT"
+    # fish uses a function instead of an env var to generate the prompt.
+
+    # Save the current fish_prompt function as the function _old_fish_prompt.
+    functions -c fish_prompt _old_fish_prompt
+
+    # With the original prompt function renamed, we can override with our own.
+    function fish_prompt
+        # Save the return status of the last command.
+        set -l old_status $status
+
+        # Output the venv prompt; color taken from the blue of the Python logo.
+        printf "%s%s%s" (set_color 4B8BBE) "(env) " (set_color normal)
+
+        # Restore the return status of the previous command.
+        echo "exit $old_status" | .
+        # Output the original/"old" prompt.
+        _old_fish_prompt
+    end
+
+    set -gx _OLD_FISH_PROMPT_OVERRIDE "$VIRTUAL_ENV"
+    set -gx VIRTUAL_ENV_PROMPT "(env) "
+end

env/bin/convert-caffe2-to-onnx

@@ -0,0 +1,8 @@
+#!/var/www/html/hugging_setup/E2-F5-TTS/env/bin/python3
+# -*- coding: utf-8 -*-
+import re
+import sys
+from caffe2.python.onnx.bin.conversion import caffe2_to_onnx
+if __name__ == '__main__':
+    sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
+    sys.exit(caffe2_to_onnx())

env/bin/convert-onnx-to-caffe2

@@ -0,0 +1,8 @@
+#!/var/www/html/hugging_setup/E2-F5-TTS/env/bin/python3
+# -*- coding: utf-8 -*-
+import re
+import sys
+from caffe2.python.onnx.bin.conversion import onnx_to_caffe2
+if __name__ == '__main__':
+    sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
+    sys.exit(onnx_to_caffe2())

env/bin/datasets-cli

@@ -0,0 +1,8 @@
+#!/var/www/html/hugging_setup/E2-F5-TTS/env/bin/python3
+# -*- coding: utf-8 -*-
+import re
+import sys
+from datasets.commands.datasets_cli import main
+if __name__ == '__main__':
+    sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
+    sys.exit(main())

env/bin/encodec

@@ -0,0 +1,8 @@
+#!/var/www/html/hugging_setup/E2-F5-TTS/env/bin/python3
+# -*- coding: utf-8 -*-
+import re
+import sys
+from encodec.__main__ import main
+if __name__ == '__main__':
+    sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
+    sys.exit(main())

env/bin/f2py

@@ -0,0 +1,8 @@
+#!/var/www/html/hugging_setup/E2-F5-TTS/env/bin/python3
+# -*- coding: utf-8 -*-
+import re
+import sys
+from numpy.f2py.f2py2e import main
+if __name__ == '__main__':
+    sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
+    sys.exit(main())

env/bin/f5-tts_finetune-cli

@@ -0,0 +1,8 @@
+#!/var/www/html/hugging_setup/E2-F5-TTS/env/bin/python3
+# -*- coding: utf-8 -*-
+import re
+import sys
+from f5_tts.train.finetune_cli import main
+if __name__ == '__main__':
+    sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
+    sys.exit(main())

env/bin/f5-tts_finetune-gradio

@@ -0,0 +1,8 @@
+#!/var/www/html/hugging_setup/E2-F5-TTS/env/bin/python3
+# -*- coding: utf-8 -*-
+import re
+import sys
+from f5_tts.train.finetune_gradio import main
+if __name__ == '__main__':
+    sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
+    sys.exit(main())

env/bin/f5-tts_infer-cli

@@ -0,0 +1,8 @@
+#!/var/www/html/hugging_setup/E2-F5-TTS/env/bin/python3
+# -*- coding: utf-8 -*-
+import re
+import sys
+from f5_tts.infer.infer_cli import main
+if __name__ == '__main__':
+    sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
+    sys.exit(main())

env/bin/f5-tts_infer-gradio

@@ -0,0 +1,8 @@
+#!/var/www/html/hugging_setup/E2-F5-TTS/env/bin/python3
+# -*- coding: utf-8 -*-
+import re
+import sys
+from f5_tts.infer.infer_gradio import main
+if __name__ == '__main__':
+    sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
+    sys.exit(main())

env/bin/fastapi

@@ -0,0 +1,8 @@
+#!/var/www/html/hugging_setup/E2-F5-TTS/env/bin/python3
+# -*- coding: utf-8 -*-
+import re
+import sys
+from fastapi.cli import main
+if __name__ == '__main__':
+    sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
+    sys.exit(main())

env/bin/fonttools

@@ -0,0 +1,8 @@
+#!/var/www/html/hugging_setup/E2-F5-TTS/env/bin/python3
+# -*- coding: utf-8 -*-
+import re
+import sys
+from fontTools.__main__ import main
+if __name__ == '__main__':
+    sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
+    sys.exit(main())

env/bin/get_gprof

@@ -0,0 +1,75 @@
+#!/var/www/html/hugging_setup/E2-F5-TTS/env/bin/python3
+#
+# Author: Mike McKerns (mmckerns @caltech and @uqfoundation)
+# Copyright (c) 2008-2016 California Institute of Technology.
+# Copyright (c) 2016-2024 The Uncertainty Quantification Foundation.
+# License: 3-clause BSD.  The full license text is available at:
+#  - https://github.com/uqfoundation/dill/blob/master/LICENSE
+'''
+build profile graph for the given instance
+
+running:
+  $ get_gprof <args> <instance>
+
+executes:
+  gprof2dot -f pstats <args> <type>.prof | dot -Tpng -o <type>.call.png
+
+where:
+  <args> are arguments for gprof2dot, such as "-n 5 -e 5"
+  <instance> is code to create the instance to profile
+  <type> is the class of the instance (i.e. type(instance))
+
+For example:
+  $ get_gprof -n 5 -e 1 "import numpy; numpy.array([1,2])"
+
+will create 'ndarray.call.png' with the profile graph for numpy.array([1,2]),
+where '-n 5' eliminates nodes below 5% threshold, similarly '-e 1' eliminates
+edges below 1% threshold
+'''
+
+if __name__ == "__main__":
+    import sys
+    if len(sys.argv) < 2:
+        print ("Please provide an object instance (e.g. 'import math; math.pi')")
+        sys.exit()
+    # grab args for gprof2dot
+    args = sys.argv[1:-1]
+    args = ' '.join(args)
+    # last arg builds the object
+    obj = sys.argv[-1]
+    obj = obj.split(';')
+    # multi-line prep for generating an instance
+    for line in obj[:-1]:
+        exec(line)
+    # one-line generation of an instance
+    try:
+        obj = eval(obj[-1])
+    except Exception:
+        print ("Error processing object instance")
+        sys.exit()
+
+    # get object 'name'
+    objtype = type(obj)
+    name = getattr(objtype, '__name__', getattr(objtype, '__class__', objtype))
+
+    # profile dumping an object
+    import dill
+    import os
+    import cProfile
+    #name = os.path.splitext(os.path.basename(__file__))[0]
+    cProfile.run("dill.dumps(obj)", filename="%s.prof" % name)
+    msg = "gprof2dot -f pstats %s %s.prof | dot -Tpng -o %s.call.png" % (args, name, name)
+    try:
+        res = os.system(msg)
+    except Exception:
+        print ("Please verify install of 'gprof2dot' to view profile graphs")
+    if res:
+        print ("Please verify install of 'gprof2dot' to view profile graphs")
+
+    # get stats
+    f_prof = "%s.prof" % name
+    import pstats
+    stats = pstats.Stats(f_prof, stream=sys.stdout)
+    stats.strip_dirs().sort_stats('cumtime')
+    stats.print_stats(20) #XXX: save to file instead of print top 20?
+    os.remove(f_prof)

env/bin/get_objgraph

@@ -0,0 +1,54 @@
+#!/var/www/html/hugging_setup/E2-F5-TTS/env/bin/python3
+#
+# Author: Mike McKerns (mmckerns @caltech and @uqfoundation)
+# Copyright (c) 2008-2016 California Institute of Technology.
+# Copyright (c) 2016-2024 The Uncertainty Quantification Foundation.
+# License: 3-clause BSD.  The full license text is available at:
+#  - https://github.com/uqfoundation/dill/blob/master/LICENSE
+"""
+display the reference paths for objects in ``dill.types`` or a .pkl file
+
+Notes:
+    the generated image is useful in showing the pointer references in
+    objects that are or can be pickled.  Any object in ``dill.objects``
+    listed in ``dill.load_types(picklable=True, unpicklable=True)`` works.
+
+Examples::
+
+    $ get_objgraph ArrayType
+    Image generated as ArrayType.png
+"""
+
+import dill as pickle
+#pickle.debug.trace(True)
+#import pickle
+
+# get all objects for testing
+from dill import load_types
+load_types(pickleable=True,unpickleable=True)
+from dill import objects
+
+if __name__ == "__main__":
+    import sys
+    if len(sys.argv) != 2:
+        print ("Please provide exactly one file or type name (e.g. 'IntType')")
+        msg = "\n"
+        for objtype in list(objects.keys())[:40]:
+            msg += objtype + ', '
+        print (msg + "...")
+    else:
+        objtype = str(sys.argv[-1])
+        try:
+            obj = objects[objtype]
+        except KeyError:
+            obj = pickle.load(open(objtype,'rb'))
+            import os
+            objtype = os.path.splitext(objtype)[0]
+        try:
+            import objgraph
+            objgraph.show_refs(obj, filename=objtype+'.png')
+        except ImportError:
+            print ("Please install 'objgraph' to view object graphs")
+
+
+# EOF

env/bin/gradio

@@ -0,0 +1,8 @@
+#!/var/www/html/hugging_setup/E2-F5-TTS/env/bin/python3
+# -*- coding: utf-8 -*-
+import re
+import sys
+from gradio.cli import cli
+if __name__ == '__main__':
+    sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
+    sys.exit(cli())

env/bin/httpx

@@ -0,0 +1,8 @@
+#!/var/www/html/hugging_setup/E2-F5-TTS/env/bin/python3
+# -*- coding: utf-8 -*-
+import re
+import sys
+from httpx import main
+if __name__ == '__main__':
+    sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
+    sys.exit(main())

env/bin/huggingface-cli

@@ -0,0 +1,8 @@
+#!/var/www/html/hugging_setup/E2-F5-TTS/env/bin/python3
+# -*- coding: utf-8 -*-
+import re
+import sys
+from huggingface_hub.commands.huggingface_cli import main
+if __name__ == '__main__':
+    sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
+    sys.exit(main())

env/bin/isympy

@@ -0,0 +1,8 @@
+#!/var/www/html/hugging_setup/E2-F5-TTS/env/bin/python3
+# -*- coding: utf-8 -*-
+import re
+import sys
+from isympy import main
+if __name__ == '__main__':
+    sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
+    sys.exit(main())