Merge pull request #9 from jhj0517/add-t2t-translation

app.py

@@ -1,7 +1,8 @@
 import gradio as gr
 from modules.whisper_Inference import WhisperInference
+from modules.nllb_inference import NLLBInference
 import os
-from ui.htmls import CSS, MARKDOWN
+from ui.htmls import *
 from modules.youtube_manager import get_ytmetas
 
 
@@ -21,6 +22,7 @@ def on_change_models(model_size):
 
 
 whisper_inf = WhisperInference()
+nllb_inf = NLLBInference()
 block = gr.Blocks(css=CSS).queue(api_open=False)
 
 with block:
@@ -100,4 +102,29 @@ with block:
             btn_openfolder.click(fn=lambda: open_fodler("outputs"), inputs=None, outputs=None)
             dd_model.change(fn=on_change_models, inputs=[dd_model], outputs=[cb_translate])
 
+        with gr.TabItem("T2T Translation"):  # tab 4
+            with gr.Row():
+                file_subs = gr.Files(type="file", label="Upload Subtitle Files to translate here",
+                                     file_types=['.vtt', '.srt'])
+
+            with gr.TabItem("NLLB"):  # sub tab1
+                with gr.Row():
+                    dd_nllb_model = gr.Dropdown(label="Model", value=nllb_inf.default_model_size,
+                                                choices=nllb_inf.available_models)
+                    dd_nllb_sourcelang = gr.Dropdown(label="Source Language", choices=nllb_inf.available_source_langs)
+                    dd_nllb_targetlang = gr.Dropdown(label="Target Language", choices=nllb_inf.available_target_langs)
+                with gr.Row():
+                    btn_run = gr.Button("TRANSLATE SUBTITLE FILE", variant="primary")
+                with gr.Row():
+                    tb_indicator = gr.Textbox(label="Output")
+                    btn_openfolder = gr.Button('📂').style(full_width=False)
+                with gr.Column():
+                    md_vram_table = gr.HTML(NLLB_VRAM_TABLE, elem_id="md_nllb_vram_table")
+
+            btn_run.click(fn=nllb_inf.translate_file,
+                          inputs=[file_subs, dd_nllb_model, dd_nllb_sourcelang, dd_nllb_targetlang],
+                          outputs=[tb_indicator])
+            btn_openfolder.click(fn=lambda: open_fodler("outputs\\translations"), inputs=None, outputs=None)
+
+
 block.launch()

modules/nllb_inference.py

@@ -0,0 +1,302 @@
+from transformers import AutoTokenizer, AutoModelForSeq2SeqLM, pipeline
+import gradio as gr
+import torch
+import os
+from datetime import datetime
+
+from modules.subtitle_manager import *
+
+DEFAULT_MODEL_SIZE = "facebook/nllb-200-1.3B"
+NLLB_MODELS = ["facebook/nllb-200-3.3B", "facebook/nllb-200-1.3B", "facebook/nllb-200-distilled-600M"]
+
+
+class NLLBInference:
+    def __init__(self):
+        self.default_model_size = DEFAULT_MODEL_SIZE
+        self.current_model_size = None
+        self.model = None
+        self.tokenizer = None
+        self.available_models = NLLB_MODELS
+        self.available_source_langs = list(NLLB_AVAILABLE_LANGS.keys())
+        self.available_target_langs = list(NLLB_AVAILABLE_LANGS.keys())
+        self.device = 0 if torch.cuda.is_available() else -1
+        self.pipeline = None
+
+    def translate_text(self, text):
+        result = self.pipeline(text)
+        return result[0]['translation_text']
+
+    def translate_file(self, fileobjs
+                       , model_size, src_lang, tgt_lang,
+                       progress=gr.Progress()):
+
+        if model_size != self.current_model_size or self.model is None:
+            print("\nInitializing NLLB Model..\n")
+            progress(0, desc="Initializing NLLB Model..")
+            self.current_model_size = model_size
+            self.model = AutoModelForSeq2SeqLM.from_pretrained(pretrained_model_name_or_path=model_size,
+                                                               cache_dir="models/NLLB")
+            self.tokenizer = AutoTokenizer.from_pretrained(pretrained_model_name_or_path=model_size,
+                                                           cache_dir=f"models/NLLB/tokenizers")
+
+        src_lang = NLLB_AVAILABLE_LANGS[src_lang]
+        tgt_lang = NLLB_AVAILABLE_LANGS[tgt_lang]
+
+        self.pipeline = pipeline("translation",
+                                 model=self.model,
+                                 tokenizer=self.tokenizer,
+                                 src_lang=src_lang,
+                                 tgt_lang=tgt_lang,
+                                 device=self.device)
+
+        files_info = {}
+        for fileobj in fileobjs:
+            file_path = fileobj.name
+            file_name, file_ext = os.path.splitext(os.path.basename(fileobj.orig_name))
+            if file_ext == ".srt":
+                parsed_dicts = parse_srt(file_path=file_path)
+                total_progress = len(parsed_dicts)
+                for index, dic in enumerate(parsed_dicts):
+                    progress(index / total_progress, desc="Translating..")
+                    translated_text = self.translate_text(dic["sentence"])
+                    dic["sentence"] = translated_text
+                subtitle = get_serialized_srt(parsed_dicts)
+
+                timestamp = datetime.now().strftime("%m%d%H%M%S")
+                file_name = file_name[:-9]
+                output_path = f"outputs/translations/{file_name}-{timestamp}"
+
+                write_file(subtitle, f"{output_path}.srt")
+
+            elif file_ext == ".vtt":
+                parsed_dicts = parse_vtt(file_path=file_path)
+                total_progress = len(parsed_dicts)
+                for index, dic in enumerate(parsed_dicts):
+                    progress(index / total_progress, desc="Translating..")
+                    translated_text = self.translate_text(dic["sentence"])
+                    dic["sentence"] = translated_text
+                subtitle = get_serialized_vtt(parsed_dicts)
+
+                timestamp = datetime.now().strftime("%m%d%H%M%S")
+                file_name = file_name[:-9]
+                output_path = f"outputs/translations/{file_name}-{timestamp}"
+
+                write_file(subtitle, f"{output_path}.vtt")
+
+            files_info[file_name] = subtitle
+
+        total_result = ''
+        for file_name, subtitle in files_info.items():
+            total_result += '------------------------------------\n'
+            total_result += f'{file_name}\n\n'
+            total_result += f'{subtitle}'
+
+        return f"Done! Subtitle is in the outputs/translation folder.\n\n{total_result}"
+
+
+NLLB_AVAILABLE_LANGS = {
+    "Acehnese (Arabic script)": "ace_Arab",
+    "Acehnese (Latin script)": "ace_Latn",
+    "Mesopotamian Arabic": "acm_Arab",
+    "Ta’izzi-Adeni Arabic": "acq_Arab",
+    "Tunisian Arabic": "aeb_Arab",
+    "Afrikaans": "afr_Latn",
+    "South Levantine Arabic": "ajp_Arab",
+    "Akan": "aka_Latn",
+    "Amharic": "amh_Ethi",
+    "North Levantine Arabic": "apc_Arab",
+    "Modern Standard Arabic": "arb_Arab",
+    "Modern Standard Arabic (Romanized)": "arb_Latn",
+    "Najdi Arabic": "ars_Arab",
+    "Moroccan Arabic": "ary_Arab",
+    "Egyptian Arabic": "arz_Arab",
+    "Assamese": "asm_Beng",
+    "Asturian": "ast_Latn",
+    "Awadhi": "awa_Deva",
+    "Central Aymara": "ayr_Latn",
+    "South Azerbaijani": "azb_Arab",
+    "North Azerbaijani": "azj_Latn",
+    "Bashkir": "bak_Cyrl",
+    "Bambara": "bam_Latn",
+    "Balinese": "ban_Latn",
+    "Belarusian": "bel_Cyrl",
+    "Bemba": "bem_Latn",
+    "Bengali": "ben_Beng",
+    "Bhojpuri": "bho_Deva",
+    "Banjar (Arabic script)": "bjn_Arab",
+    "Banjar (Latin script)": "bjn_Latn",
+    "Standard Tibetan": "bod_Tibt",
+    "Bosnian": "bos_Latn",
+    "Buginese": "bug_Latn",
+    "Bulgarian": "bul_Cyrl",
+    "Catalan": "cat_Latn",
+    "Cebuano": "ceb_Latn",
+    "Czech": "ces_Latn",
+    "Chokwe": "cjk_Latn",
+    "Central Kurdish": "ckb_Arab",
+    "Crimean Tatar": "crh_Latn",
+    "Welsh": "cym_Latn",
+    "Danish": "dan_Latn",
+    "German": "deu_Latn",
+    "Southwestern Dinka": "dik_Latn",
+    "Dyula": "dyu_Latn",
+    "Dzongkha": "dzo_Tibt",
+    "Greek": "ell_Grek",
+    "English": "eng_Latn",
+    "Esperanto": "epo_Latn",
+    "Estonian": "est_Latn",
+    "Basque": "eus_Latn",
+    "Ewe": "ewe_Latn",
+    "Faroese": "fao_Latn",
+    "Fijian": "fij_Latn",
+    "Finnish": "fin_Latn",
+    "Fon": "fon_Latn",
+    "French": "fra_Latn",
+    "Friulian": "fur_Latn",
+    "Nigerian Fulfulde": "fuv_Latn",
+    "Scottish Gaelic": "gla_Latn",
+    "Irish": "gle_Latn",
+    "Galician": "glg_Latn",
+    "Guarani": "grn_Latn",
+    "Gujarati": "guj_Gujr",
+    "Haitian Creole": "hat_Latn",
+    "Hausa": "hau_Latn",
+    "Hebrew": "heb_Hebr",
+    "Hindi": "hin_Deva",
+    "Chhattisgarhi": "hne_Deva",
+    "Croatian": "hrv_Latn",
+    "Hungarian": "hun_Latn",
+    "Armenian": "hye_Armn",
+    "Igbo": "ibo_Latn",
+    "Ilocano": "ilo_Latn",
+    "Indonesian": "ind_Latn",
+    "Icelandic": "isl_Latn",
+    "Italian": "ita_Latn",
+    "Javanese": "jav_Latn",
+    "Japanese": "jpn_Jpan",
+    "Kabyle": "kab_Latn",
+    "Jingpho": "kac_Latn",
+    "Kamba": "kam_Latn",
+    "Kannada": "kan_Knda",
+    "Kashmiri (Arabic script)": "kas_Arab",
+    "Kashmiri (Devanagari script)": "kas_Deva",
+    "Georgian": "kat_Geor",
+    "Central Kanuri (Arabic script)": "knc_Arab",
+    "Central Kanuri (Latin script)": "knc_Latn",
+    "Kazakh": "kaz_Cyrl",
+    "Kabiyè": "kbp_Latn",
+    "Kabuverdianu": "kea_Latn",
+    "Khmer": "khm_Khmr",
+    "Kikuyu": "kik_Latn",
+    "Kinyarwanda": "kin_Latn",
+    "Kyrgyz": "kir_Cyrl",
+    "Kimbundu": "kmb_Latn",
+    "Northern Kurdish": "kmr_Latn",
+    "Kikongo": "kon_Latn",
+    "Korean": "kor_Hang",
+    "Lao": "lao_Laoo",
+    "Ligurian": "lij_Latn",
+    "Limburgish": "lim_Latn",
+    "Lingala": "lin_Latn",
+    "Lithuanian": "lit_Latn",
+    "Lombard": "lmo_Latn",
+    "Latgalian": "ltg_Latn",
+    "Luxembourgish": "ltz_Latn",
+    "Luba-Kasai": "lua_Latn",
+    "Ganda": "lug_Latn",
+    "Luo": "luo_Latn",
+    "Mizo": "lus_Latn",
+    "Standard Latvian": "lvs_Latn",
+    "Magahi": "mag_Deva",
+    "Maithili": "mai_Deva",
+    "Malayalam": "mal_Mlym",
+    "Marathi": "mar_Deva",
+    "Minangkabau (Arabic script)": "min_Arab",
+    "Minangkabau (Latin script)": "min_Latn",
+    "Macedonian": "mkd_Cyrl",
+    "Plateau Malagasy": "plt_Latn",
+    "Maltese": "mlt_Latn",
+    "Meitei (Bengali script)": "mni_Beng",
+    "Halh Mongolian": "khk_Cyrl",
+    "Mossi": "mos_Latn",
+    "Maori": "mri_Latn",
+    "Burmese": "mya_Mymr",
+    "Dutch": "nld_Latn",
+    "Norwegian Nynorsk": "nno_Latn",
+    "Norwegian Bokmål": "nob_Latn",
+    "Nepali": "npi_Deva",
+    "Northern Sotho": "nso_Latn",
+    "Nuer": "nus_Latn",
+    "Nyanja": "nya_Latn",
+    "Occitan": "oci_Latn",
+    "West Central Oromo": "gaz_Latn",
+    "Odia": "ory_Orya",
+    "Pangasinan": "pag_Latn",
+    "Eastern Panjabi": "pan_Guru",
+    "Papiamento": "pap_Latn",
+    "Western Persian": "pes_Arab",
+    "Polish": "pol_Latn",
+    "Portuguese": "por_Latn",
+    "Dari": "prs_Arab",
+    "Southern Pashto": "pbt_Arab",
+    "Ayacucho Quechua": "quy_Latn",
+    "Romanian": "ron_Latn",
+    "Rundi": "run_Latn",
+    "Russian": "rus_Cyrl",
+    "Sango": "sag_Latn",
+    "Sanskrit": "san_Deva",
+    "Santali": "sat_Olck",
+    "Sicilian": "scn_Latn",
+    "Shan": "shn_Mymr",
+    "Sinhala": "sin_Sinh",
+    "Slovak": "slk_Latn",
+    "Slovenian": "slv_Latn",
+    "Samoan": "smo_Latn",
+    "Shona": "sna_Latn",
+    "Sindhi": "snd_Arab",
+    "Somali": "som_Latn",
+    "Southern Sotho": "sot_Latn",
+    "Spanish": "spa_Latn",
+    "Tosk Albanian": "als_Latn",
+    "Sardinian": "srd_Latn",
+    "Serbian": "srp_Cyrl",
+    "Swati": "ssw_Latn",
+    "Sundanese": "sun_Latn",
+    "Swedish": "swe_Latn",
+    "Swahili": "swh_Latn",
+    "Silesian": "szl_Latn",
+    "Tamil": "tam_Taml",
+    "Tatar": "tat_Cyrl",
+    "Telugu": "tel_Telu",
+    "Tajik": "tgk_Cyrl",
+    "Tagalog": "tgl_Latn",
+    "Thai": "tha_Thai",
+    "Tigrinya": "tir_Ethi",
+    "Tamasheq (Latin script)": "taq_Latn",
+    "Tamasheq (Tifinagh script)": "taq_Tfng",
+    "Tok Pisin": "tpi_Latn",
+    "Tswana": "tsn_Latn",
+    "Tsonga": "tso_Latn",
+    "Turkmen": "tuk_Latn",
+    "Tumbuka": "tum_Latn",
+    "Turkish": "tur_Latn",
+    "Twi": "twi_Latn",
+    "Central Atlas Tamazight": "tzm_Tfng",
+    "Uyghur": "uig_Arab",
+    "Ukrainian": "ukr_Cyrl",
+    "Umbundu": "umb_Latn",
+    "Urdu": "urd_Arab",
+    "Northern Uzbek": "uzn_Latn",
+    "Venetian": "vec_Latn",
+    "Vietnamese": "vie_Latn",
+    "Waray": "war_Latn",
+    "Wolof": "wol_Latn",
+    "Xhosa": "xho_Latn",
+    "Eastern Yiddish": "ydd_Hebr",
+    "Yoruba": "yor_Latn",
+    "Yue Chinese": "yue_Hant",
+    "Chinese (Simplified)": "zho_Hans",
+    "Chinese (Traditional)": "zho_Hant",
+    "Standard Malay": "zsm_Latn",
+    "Zulu": "zul_Latn",
+}

ui/htmls.py

@@ -39,4 +39,59 @@ CSS = """
 
 MARKDOWN = """
 ### [Whisper Web-UI](https://github.com/jhj0517/Whsiper-WebUI)
+"""
+
+
+NLLB_VRAM_TABLE = """
+<!DOCTYPE html>
+<html lang="en">
+<head>
+  <meta charset="UTF-8">
+  <meta name="viewport" content="width=device-width, initial-scale=1.0">
+  <style>
+    table {
+      border-collapse: collapse;
+      width: 100%;
+    }
+    th, td {
+      border: 1px solid #dddddd;
+      text-align: left;
+      padding: 8px;
+    }
+    th {
+      background-color: #f2f2f2;
+    }
+  </style>
+</head>
+<body>
+
+<details>
+  <summary>VRAM usage for each model</summary>
+  <table>
+    <thead>
+      <tr>
+        <th>Model name</th>
+        <th>Required VRAM</th>
+      </tr>
+    </thead>
+    <tbody>
+      <tr>
+        <td>nllb-200-3.3B</td>
+        <td>~16GB</td>
+      </tr>
+      <tr>
+        <td>nllb-200-1.3B</td>
+        <td>~8GB</td>
+      </tr>
+      <tr>
+        <td>nllb-200-distilled-600M</td>
+        <td>~4GB</td>
+      </tr>
+    </tbody>
+  </table>
+  <p><strong>Note:</strong> Be mindful of your VRAM! The table above provides an approximate VRAM usage for each model.</p>
+</details>
+
+</body>
+</html>
 """