Training in progress, step 300

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "openai/whisper-large",
+  "_name_or_path": "openai/whisper-base",
   "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": 1280,
-  "decoder_attention_heads": 20,
-  "decoder_ffn_dim": 5120,
+  "d_model": 512,
+  "decoder_attention_heads": 8,
+  "decoder_ffn_dim": 2048,
   "decoder_layerdrop": 0.0,
-  "decoder_layers": 32,
+  "decoder_layers": 6,
   "decoder_start_token_id": 50258,
   "dropout": 0.0,
-  "encoder_attention_heads": 20,
-  "encoder_ffn_dim": 5120,
+  "encoder_attention_heads": 8,
+  "encoder_ffn_dim": 2048,
   "encoder_layerdrop": 0.0,
-  "encoder_layers": 32,
+  "encoder_layers": 6,
   "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": 32,
+  "num_hidden_layers": 6,
   "num_mel_bins": 80,
   "pad_token_id": 50257,
   "scale_embedding": false,

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e52678573e5d211790196e1a1daf7bd14a80a5663f233dbae7c7f557a043101
+size 290403936

runs/May29_01-48-52_7de60d084772/events.out.tfevents.1716947346.7de60d084772.176.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c01a431c35a72d50d9275a88f91eb40d8224e9c35b2a7bbf8183aa60c8ee3430
+size 8512

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17aa024a04b4d3ff813e102a135712d9cfd7c89676a5217bed621da168eb5a39
+oid sha256:6dc2f2c40e08c6fad1db0b02f897c3826b326e7fd526f1892e6d22acc53f5ed2
 size 5240