Training in progress, step 400

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "openai/whisper-large",
+  "_name_or_path": "openai/whisper-medium",
   "activation_dropout": 0.0,
   "activation_function": "gelu",
   "apply_spec_augment": false,
@@ -13,17 +13,17 @@
   ],
   "bos_token_id": 50257,
   "classifier_proj_size": 256,
-  "d_model": 1280,
-  "decoder_attention_heads": 20,
-  "decoder_ffn_dim": 5120,
+  "d_model": 1024,
+  "decoder_attention_heads": 16,
+  "decoder_ffn_dim": 4096,
   "decoder_layerdrop": 0.0,
-  "decoder_layers": 32,
+  "decoder_layers": 24,
   "decoder_start_token_id": 50258,
   "dropout": 0.0,
-  "encoder_attention_heads": 20,
-  "encoder_ffn_dim": 5120,
+  "encoder_attention_heads": 16,
+  "encoder_ffn_dim": 4096,
   "encoder_layerdrop": 0.0,
-  "encoder_layers": 32,
+  "encoder_layers": 24,
   "eos_token_id": 50257,
   "forced_decoder_ids": null,
   "init_std": 0.02,
@@ -39,13 +39,13 @@
   "max_target_positions": 448,
   "median_filter_width": 7,
   "model_type": "whisper",
-  "num_hidden_layers": 32,
+  "num_hidden_layers": 24,
   "num_mel_bins": 80,
   "pad_token_id": 50257,
   "scale_embedding": false,
   "suppress_tokens": [],
   "torch_dtype": "float32",
-  "transformers_version": "4.35.0.dev0",
+  "transformers_version": "4.36.0.dev0",
   "use_cache": false,
   "use_weighted_layer_sum": false,
   "vocab_size": 51865

generation_config.json

@@ -1,40 +1,28 @@
 {
   "alignment_heads": [
     [
-      9,
-      19
-    ],
-    [
-      11,
-      2
+      13,
+      15
     ],
     [
-      11,
+      15,
       4
     ],
     [
-      11,
-      17
-    ],
-    [
-      22,
-      7
-    ],
-    [
-      22,
-      11
+      15,
+      15
     ],
     [
-      22,
-      17
+      16,
+      1
     ],
     [
-      23,
-      2
+      20,
+      0
     ],
     [
       23,
-      15
+      4
     ]
   ],
   "begin_suppress_tokens": [
@@ -160,7 +148,6 @@
   "max_length": 448,
   "no_timestamps_token_id": 50363,
   "pad_token_id": 50257,
-  "return_timestamps": false,
   "suppress_tokens": [
     1,
     2,
@@ -255,5 +242,5 @@
     "transcribe": 50359,
     "translate": 50358
   },
-  "transformers_version": "4.35.0.dev0"
+  "transformers_version": "4.36.0.dev0"
 }

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16c17158d246b866cc2702254feab189566860c45f747aa9ed59078c0c1b9db8
+size 3055544304

runs/Nov09_00-55-03_fe6aa5ad26c2/events.out.tfevents.1699491320.fe6aa5ad26c2.2517.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f711480132730b251c207fe823a7f3cf66d38ad8c886d0e7d727967fcf43b5a
+size 23982

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4a2990d4d130b42cf8fbfa7ba8f574eb43332601e76d83396fa2a0897d71d41
-size 4664
+oid sha256:2a5d8b19bdd650c6ee71274645f3009ebf411f8bfe420285cdb1318653e53bd7
+size 4728