Training in progress, step 100

config.json

@@ -1,7 +1,8 @@
 {
-  "_name_or_path": "/home/hclspeech/Desktop/prashanth/VM/whisper2",
+  "_name_or_path": "openai/whisper-small.en",
   "activation_dropout": 0.0,
   "activation_function": "gelu",
+  "apply_spec_augment": false,
   "architectures": [
     "WhisperForConditionalGeneration"
   ],
@@ -11,32 +12,40 @@
     50256
   ],
   "bos_token_id": 50257,
-  "d_model": 512,
-  "decoder_attention_heads": 8,
-  "decoder_ffn_dim": 2048,
+  "classifier_proj_size": 256,
+  "d_model": 768,
+  "decoder_attention_heads": 12,
+  "decoder_ffn_dim": 3072,
   "decoder_layerdrop": 0.0,
-  "decoder_layers": 6,
+  "decoder_layers": 12,
   "decoder_start_token_id": 50257,
   "dropout": 0.0,
-  "encoder_attention_heads": 8,
-  "encoder_ffn_dim": 2048,
+  "encoder_attention_heads": 12,
+  "encoder_ffn_dim": 3072,
   "encoder_layerdrop": 0.0,
-  "encoder_layers": 6,
+  "encoder_layers": 12,
   "eos_token_id": 50256,
   "forced_decoder_ids": null,
   "init_std": 0.02,
   "is_encoder_decoder": true,
+  "mask_feature_length": 10,
+  "mask_feature_min_masks": 0,
+  "mask_feature_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_min_masks": 2,
+  "mask_time_prob": 0.05,
   "max_length": 448,
   "max_source_positions": 1500,
   "max_target_positions": 448,
   "model_type": "whisper",
-  "num_hidden_layers": 6,
+  "num_hidden_layers": 12,
   "num_mel_bins": 80,
   "pad_token_id": 50256,
   "scale_embedding": false,
   "suppress_tokens": [],
   "torch_dtype": "float32",
-  "transformers_version": "4.24.0",
+  "transformers_version": "4.28.0.dev0",
   "use_cache": true,
+  "use_weighted_layer_sum": false,
   "vocab_size": 51864
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:08e42b612a6ae326dcaf673232af99ed9d64f997ea2aa87154c15da3d5d34ab9
-size 290454551
+oid sha256:d7cc76da87490f887180cf5c13a342cf47ccf43a158c88621591607c9a373c41
+size 967092809

runs/Apr04_06-01-23_voice-dsvm/1680588225.770872/events.out.tfevents.1680588225.voice-dsvm.683381.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a21c6d65c77a6a6aa846cbf92dca87af1b3454859989c09362da53ee8fa4b171
+size 6019

runs/Apr04_06-01-23_voice-dsvm/events.out.tfevents.1680588225.voice-dsvm.683381.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e22fabee59f10dc44b03932b01844a8bd6ee761dcb37663ce79c2fc15dfaac6
+size 5633

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53c843c6daa88155645642b504af924ce8c7baf10ff0400eeaf7b8783dfc70a8
-size 3503
+oid sha256:6747c38a8ae8b8dbfcd3e0a81a1eeb02e181d7901bd1d0cc5149990896bd9a35
+size 3707