Training in progress, step 100

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "openai/whisper-base",
+  "_name_or_path": "openai/whisper-large-v3-turbo",
   "activation_dropout": 0.0,
   "activation_function": "gelu",
   "apply_spec_augment": false,
@@ -7,20 +7,23 @@
     "WhisperForConditionalGeneration"
   ],
   "attention_dropout": 0.0,
-  "begin_suppress_tokens": null,
+  "begin_suppress_tokens": [
+    220,
+    50256
+  ],
   "bos_token_id": 50257,
   "classifier_proj_size": 256,
-  "d_model": 512,
-  "decoder_attention_heads": 8,
-  "decoder_ffn_dim": 2048,
+  "d_model": 1280,
+  "decoder_attention_heads": 20,
+  "decoder_ffn_dim": 5120,
   "decoder_layerdrop": 0.0,
-  "decoder_layers": 6,
+  "decoder_layers": 4,
   "decoder_start_token_id": 50258,
   "dropout": 0.0,
-  "encoder_attention_heads": 8,
-  "encoder_ffn_dim": 2048,
+  "encoder_attention_heads": 20,
+  "encoder_ffn_dim": 5120,
   "encoder_layerdrop": 0.0,
-  "encoder_layers": 6,
+  "encoder_layers": 32,
   "eos_token_id": 50257,
   "forced_decoder_ids": null,
   "init_std": 0.02,
@@ -31,18 +34,17 @@
   "mask_time_length": 10,
   "mask_time_min_masks": 2,
   "mask_time_prob": 0.05,
-  "max_length": null,
   "max_source_positions": 1500,
   "max_target_positions": 448,
   "median_filter_width": 7,
   "model_type": "whisper",
-  "num_hidden_layers": 6,
-  "num_mel_bins": 80,
+  "num_hidden_layers": 32,
+  "num_mel_bins": 128,
   "pad_token_id": 50257,
   "scale_embedding": false,
   "torch_dtype": "float32",
   "transformers_version": "4.47.0.dev0",
   "use_cache": true,
   "use_weighted_layer_sum": false,
-  "vocab_size": 51865
+  "vocab_size": 51866
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3ba8eedb45dc2115163a35b05bd55d0f0e05ebd9c79b869daafcbd3e4962f50
-size 290403936
+oid sha256:092b14fa6ae51fe26f24fc25d4245f66b755b36184b5592a77bdca2d92ff6dc1
+size 3235581408

preprocessor_config.json

@@ -1,7 +1,7 @@
 {
   "chunk_length": 30,
   "feature_extractor_type": "WhisperFeatureExtractor",
-  "feature_size": 80,
+  "feature_size": 128,
   "hop_length": 160,
   "n_fft": 400,
   "n_samples": 480000,

runs/Nov14_04-29-17_6ba365f8b3aa/events.out.tfevents.1731558590.6ba365f8b3aa.3377.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8510eba0e3bce3ea69ee34b5ca9e85eefac8161f6e9217d99e8a895bcf35cb50
+size 5874

runs/Nov14_04-34-22_6ba365f8b3aa/events.out.tfevents.1731558875.6ba365f8b3aa.3377.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c97ed4b94924b7dbfc8de7b0be7ea5f940086b64f2520c901dd50e48ae45b40e
+size 7050

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de50844fb2d4cc81ff5ddc70c493374a3ce58bab29c67a61854b72b456322400
+oid sha256:6afa3df01d252d768d46648c2e6458d2b2bf9dffb6108bbfb8f6e51b78385ac8
 size 5496