Training in progress, step 1000

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "openai/whisper-small",
+  "_name_or_path": "openai/whisper-large",
   "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": 768,
-  "decoder_attention_heads": 12,
-  "decoder_ffn_dim": 3072,
+  "d_model": 1280,
+  "decoder_attention_heads": 20,
+  "decoder_ffn_dim": 5120,
   "decoder_layerdrop": 0.0,
-  "decoder_layers": 12,
+  "decoder_layers": 32,
   "decoder_start_token_id": 50258,
   "dropout": 0.0,
-  "encoder_attention_heads": 12,
-  "encoder_ffn_dim": 3072,
+  "encoder_attention_heads": 20,
+  "encoder_ffn_dim": 5120,
   "encoder_layerdrop": 0.0,
-  "encoder_layers": 12,
+  "encoder_layers": 32,
   "eos_token_id": 50257,
   "forced_decoder_ids": null,
   "init_std": 0.02,
@@ -39,13 +39,13 @@
   "max_target_positions": 448,
   "median_filter_width": 7,
   "model_type": "whisper",
-  "num_hidden_layers": 12,
+  "num_hidden_layers": 32,
   "num_mel_bins": 80,
   "pad_token_id": 50257,
   "scale_embedding": false,
   "suppress_tokens": [],
   "torch_dtype": "float32",
-  "transformers_version": "4.32.0.dev0",
+  "transformers_version": "4.33.0.dev0",
   "use_cache": true,
   "use_weighted_layer_sum": false,
   "vocab_size": 51865

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7fc3178c82d552339fb9e0c8e9e7c2b3d5b05a1a8c3a6f2c6cfe6e5ec2d1463c
-size 967102729
+oid sha256:b514318b402cc04c06dbf6cd1aa605e82d0cc118ce62c659b2a84cc66b351085
+size 6173655608

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36ade95197432ccd97a8ddfe6dfb5056490ec5b6efed4ea2ee83a7fd792cc1cc
+oid sha256:f0f57ab1d3725bff21755b6c4c7e022d21baebb74264d7587dd67f21715bdc91
 size 4155