gweltou commited on
Commit
a3c8f1c
1 Parent(s): dadc81c

Training in progress, step 500

Browse files
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "openai/whisper-small",
3
  "activation_dropout": 0.0,
4
  "activation_function": "gelu",
5
  "apply_spec_augment": false,
@@ -13,17 +13,17 @@
13
  ],
14
  "bos_token_id": 50257,
15
  "classifier_proj_size": 256,
16
- "d_model": 768,
17
- "decoder_attention_heads": 12,
18
- "decoder_ffn_dim": 3072,
19
  "decoder_layerdrop": 0.0,
20
- "decoder_layers": 12,
21
  "decoder_start_token_id": 50258,
22
  "dropout": 0.0,
23
- "encoder_attention_heads": 12,
24
- "encoder_ffn_dim": 3072,
25
  "encoder_layerdrop": 0.0,
26
- "encoder_layers": 12,
27
  "eos_token_id": 50257,
28
  "forced_decoder_ids": null,
29
  "init_std": 0.02,
@@ -39,7 +39,7 @@
39
  "max_target_positions": 448,
40
  "median_filter_width": 7,
41
  "model_type": "whisper",
42
- "num_hidden_layers": 12,
43
  "num_mel_bins": 80,
44
  "pad_token_id": 50257,
45
  "scale_embedding": false,
 
1
  {
2
+ "_name_or_path": "openai/whisper-base",
3
  "activation_dropout": 0.0,
4
  "activation_function": "gelu",
5
  "apply_spec_augment": false,
 
13
  ],
14
  "bos_token_id": 50257,
15
  "classifier_proj_size": 256,
16
+ "d_model": 512,
17
+ "decoder_attention_heads": 8,
18
+ "decoder_ffn_dim": 2048,
19
  "decoder_layerdrop": 0.0,
20
+ "decoder_layers": 6,
21
  "decoder_start_token_id": 50258,
22
  "dropout": 0.0,
23
+ "encoder_attention_heads": 8,
24
+ "encoder_ffn_dim": 2048,
25
  "encoder_layerdrop": 0.0,
26
+ "encoder_layers": 6,
27
  "eos_token_id": 50257,
28
  "forced_decoder_ids": null,
29
  "init_std": 0.02,
 
39
  "max_target_positions": 448,
40
  "median_filter_width": 7,
41
  "model_type": "whisper",
42
+ "num_hidden_layers": 6,
43
  "num_mel_bins": 80,
44
  "pad_token_id": 50257,
45
  "scale_embedding": false,
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7335724d049c8f79b6fce8fd4f587fa26888e16405c23b1fe9c117fa71fabea9
3
- size 966995080
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b96cdb55720e5f06382dc7a74ace281477428654593ef97a6bff06b1e2cd20fb
3
+ size 290403936
runs/Jan17_17-22-13_3fb1a8037d9c/events.out.tfevents.1705512157.3fb1a8037d9c.399.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ccdbe02406c94be749a6becb505e770b3e7a95b374aa7c8e88e56b63edd68f05
3
+ size 6571
tokenizer_config.json CHANGED
@@ -12980,7 +12980,7 @@
12980
  "clean_up_tokenization_spaces": true,
12981
  "eos_token": "<|endoftext|>",
12982
  "errors": "replace",
12983
- "model_max_length": 1024,
12984
  "pad_token": "<|endoftext|>",
12985
  "processor_class": "WhisperProcessor",
12986
  "return_attention_mask": false,
 
12980
  "clean_up_tokenization_spaces": true,
12981
  "eos_token": "<|endoftext|>",
12982
  "errors": "replace",
12983
+ "model_max_length": 448,
12984
  "pad_token": "<|endoftext|>",
12985
  "processor_class": "WhisperProcessor",
12986
  "return_attention_mask": false,
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c4a9b46c13336263af534635bd839dc4cff2c2af0fa17a16dfe18e6d3754d05e
3
  size 4728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc2e73cdda8257333a1ff484734cbec89e0eac555048409375d15fcadc3075bf
3
  size 4728