Training in progress, step 500

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "openai/whisper-small",
+  "_name_or_path": "openai/whisper-medium",
   "activation_dropout": 0.0,
   "activation_function": "gelu",
   "apply_spec_augment": false,
@@ -10,17 +10,17 @@
   "begin_suppress_tokens": null,
   "bos_token_id": 50257,
   "classifier_proj_size": 256,
-  "d_model": 768,
-  "decoder_attention_heads": 12,
-  "decoder_ffn_dim": 3072,
+  "d_model": 1024,
+  "decoder_attention_heads": 16,
+  "decoder_ffn_dim": 4096,
   "decoder_layerdrop": 0.0,
-  "decoder_layers": 12,
+  "decoder_layers": 24,
   "decoder_start_token_id": 50258,
   "dropout": 0.0,
-  "encoder_attention_heads": 12,
-  "encoder_ffn_dim": 3072,
+  "encoder_attention_heads": 16,
+  "encoder_ffn_dim": 4096,
   "encoder_layerdrop": 0.0,
-  "encoder_layers": 12,
+  "encoder_layers": 24,
   "eos_token_id": 50257,
   "forced_decoder_ids": null,
   "init_std": 0.02,
@@ -36,12 +36,12 @@
   "max_target_positions": 448,
   "median_filter_width": 7,
   "model_type": "whisper",
-  "num_hidden_layers": 12,
+  "num_hidden_layers": 24,
   "num_mel_bins": 80,
   "pad_token_id": 50257,
   "scale_embedding": false,
   "torch_dtype": "float32",
-  "transformers_version": "4.47.1",
+  "transformers_version": "4.45.2",
   "use_cache": false,
   "use_weighted_layer_sum": false,
   "vocab_size": 51865

generation_config.json

@@ -1,44 +1,28 @@
 {
   "alignment_heads": [
     [
-      5,
-      3
+      13,
+      15
     ],
     [
-      5,
-      9
-    ],
-    [
-      8,
-      0
-    ],
-    [
-      8,
+      15,
       4
     ],
     [
-      8,
-      7
+      15,
+      15
     ],
     [
-      8,
-      8
+      16,
+      1
     ],
     [
-      9,
+      20,
       0
     ],
     [
-      9,
-      7
-    ],
-    [
-      9,
-      9
-    ],
-    [
-      10,
-      5
+      23,
+      4
     ]
   ],
   "begin_suppress_tokens": [
@@ -167,10 +151,9 @@
   "prev_sot_token_id": 50361,
   "return_timestamps": false,
   "suppress_tokens": [],
-  "task": "translate",
   "task_to_id": {
     "transcribe": 50359,
     "translate": 50358
   },
-  "transformers_version": "4.47.1"
+  "transformers_version": "4.45.2"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bdefad703740be8e8fc727ef0190c02293f995d5409e2629a0fa7025711f8887
-size 966995080
+oid sha256:d466755a1a30d434549d67e057edcbcbd5f1a7102acec7cb0879edeeba5d44b0
+size 3055544304

runs/Jan08_19-13-32_c402324bf046/events.out.tfevents.1736363666.c402324bf046.1243.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59839f30bface808efd878b93243c1dddf0ddcb5e271a7c00e19043df938c489
+size 10311

tokenizer_config.json

@@ -12980,7 +12980,6 @@
   "clean_up_tokenization_spaces": true,
   "eos_token": "<|endoftext|>",
   "errors": "replace",
-  "extra_special_tokens": {},
   "model_max_length": 1024,
   "pad_token": "<|endoftext|>",
   "processor_class": "WhisperProcessor",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:372e07cee47c45bcdd99e97e1b2703a6f6de7c5aa4679f0b1cdbb5af398ea79c
-size 5496
+oid sha256:b8ec4a8c94855f951db9e8fdbf01881b00e1cd380781a427edc3562bec4a1238
+size 5368