Training in progress, step 2000

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "openai/whisper-tiny",
+  "_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": 384,
-  "decoder_attention_heads": 6,
-  "decoder_ffn_dim": 1536,
+  "d_model": 768,
+  "decoder_attention_heads": 12,
+  "decoder_ffn_dim": 3072,
   "decoder_layerdrop": 0.0,
-  "decoder_layers": 4,
+  "decoder_layers": 12,
   "decoder_start_token_id": 50258,
   "dropout": 0.0,
-  "encoder_attention_heads": 6,
-  "encoder_ffn_dim": 1536,
+  "encoder_attention_heads": 12,
+  "encoder_ffn_dim": 3072,
   "encoder_layerdrop": 0.0,
-  "encoder_layers": 4,
+  "encoder_layers": 12,
   "eos_token_id": 50257,
   "forced_decoder_ids": [
     [
@@ -49,7 +49,7 @@
   "max_target_positions": 448,
   "median_filter_width": 7,
   "model_type": "whisper",
-  "num_hidden_layers": 4,
+  "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 sha256:65b11f982c0e31912f464b4b359cc505f6176aa4638c39fbb589e012623181da
-size 151061672
+oid sha256:85dd453f4b2db6a98c14bcfe0f805e9e75fbe4c96d8a342ee7ad772a4b1f9de0
+size 966995080

runs/Nov26_13-30-38_fd83b97470de/events.out.tfevents.1732627875.fd83b97470de.234.1

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97bff1a96979809f123f95225018313052fea846c9ec69aea50c892aa2df8244
-size 20448
+oid sha256:7a5f9e1a1acfaddfb987cc2922b1541164161aaad05a1310176e5a881dafbfb1
+size 25340

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39b33cfad1fa48f6310cbd6f0b1b3b9d689815a9b4514e5ed8e78b1185d68613
+oid sha256:a1749b76e9de0027bb20a3425957ddf69775166ef876c174d5bb0ef7d1ba065f
 size 5432