Training in progress, step 1000

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "openai/whisper-base",
+  "_name_or_path": "openai/whisper-small",
   "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": 512,
-  "decoder_attention_heads": 8,
-  "decoder_ffn_dim": 2048,
+  "d_model": 768,
+  "decoder_attention_heads": 12,
+  "decoder_ffn_dim": 3072,
   "decoder_layerdrop": 0.0,
-  "decoder_layers": 6,
+  "decoder_layers": 12,
   "decoder_start_token_id": 50258,
   "dropout": 0.0,
-  "encoder_attention_heads": 8,
-  "encoder_ffn_dim": 2048,
+  "encoder_attention_heads": 12,
+  "encoder_ffn_dim": 3072,
   "encoder_layerdrop": 0.0,
-  "encoder_layers": 6,
+  "encoder_layers": 12,
   "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": 6,
+  "num_hidden_layers": 12,
   "num_mel_bins": 80,
   "pad_token_id": 50257,
   "scale_embedding": false,
   "torch_dtype": "float32",
-  "transformers_version": "4.46.1",
+  "transformers_version": "4.48.1",
   "use_cache": true,
   "use_weighted_layer_sum": false,
   "vocab_size": 51865

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3df68fc630788b734586e4e9cfc056cbba9b5756855fbd863e20e5917afeec4
-size 290403936
+oid sha256:76ad8464abda0e70dbd57ba2f6162afcad62cb95f843fb9336310525bcdb3f34
+size 966995080

runs/Dec27_13-17-28_DESKTOP-BCLBGEN/events.out.tfevents.1735273149.DESKTOP-BCLBGEN.1592.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:378534a29f6121284d7e13da24133957f4ceb17285b48af23f78fbf28a9c6a34
-size 154761
+oid sha256:1853ceb00810e173358abd2e7784204f77b6246a1a962a4be0921cabcbb565ed
+size 161856

runs/Jan24_10-21-43_DESKTOP-BCLBGEN/events.out.tfevents.1737682108.DESKTOP-BCLBGEN.13220.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b9e1dd65e7d25cefc9538aeee5449bac9812587831d8912439c399215a420d0
+size 28330

runs/Jan24_11-19-16_DESKTOP-BCLBGEN/events.out.tfevents.1737685158.DESKTOP-BCLBGEN.16112.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:991965fb66caa5d5e9c27c155a3df2c84a1548f72c4debf8b15e9bcf4fd35aec
+size 14574

tokenizer_config.json

@@ -12980,6 +12980,7 @@
   "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 sha256:63de9a3887c2c84d11e8306965a0a23283c054356b7e9f1c83cc7d0a889f8587
-size 5368
+oid sha256:327402e86d4b3de4025369025558189132301135016d794922ee098bf6b12de2
+size 5432