Training in progress, step 1000

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "openai/whisper-medium",
+  "_name_or_path": "openai/whisper-small",
   "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": 1024,
-  "decoder_attention_heads": 16,
-  "decoder_ffn_dim": 4096,
+  "d_model": 768,
+  "decoder_attention_heads": 12,
+  "decoder_ffn_dim": 3072,
   "decoder_layerdrop": 0.0,
-  "decoder_layers": 24,
+  "decoder_layers": 12,
   "decoder_start_token_id": 50258,
   "dropout": 0.0,
-  "encoder_attention_heads": 16,
-  "encoder_ffn_dim": 4096,
+  "encoder_attention_heads": 12,
+  "encoder_ffn_dim": 3072,
   "encoder_layerdrop": 0.0,
-  "encoder_layers": 24,
+  "encoder_layers": 12,
   "eos_token_id": 50257,
   "forced_decoder_ids": null,
   "init_std": 0.02,
@@ -39,7 +39,7 @@
   "max_target_positions": 448,
   "median_filter_width": 7,
   "model_type": "whisper",
-  "num_hidden_layers": 24,
+  "num_hidden_layers": 12,
   "num_mel_bins": 80,
   "pad_token_id": 50257,
   "scale_embedding": false,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:881d9e8c1a08cca38c16a675bb9c590f70504b8e7d0fa1be38f04cfbcc24e6e1
-size 3055544304
+oid sha256:ff745bdabf072cf62e4b709ffe56f540df4f0e04d98682d74470534dcca0f00e
+size 966995080

runs/Mar30_09-36-18_b03f800a85e6/events.out.tfevents.1711791418.b03f800a85e6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ff2e3801aeedcf500f882f3f6f6332e71ad2ef62d950fe4fdd33daf1f98bf55
+size 14182

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c66f04e6272ca0ecd53c18ec5335c8beb7661863ba3348cb4042a7bd025c8b66
-size 5048
+oid sha256:fa5c47b706f4f0ace1844480c75f8b0a133f67848efd7504100725e2e384ce2a
+size 5112