Hugging Face's logo

RobbieJimersonJr
/
whisper-small-Seneca

Automatic Speech Recognition
Transformers
PyTorch
whisper
whisper-event
Generated from Trainer
Eval Results (legacy)
Model card Files
xet
 Community
1
RobbieJimersonJr commited on
Commit
e420bb1
·
1 Parent(s): e74b38e

Training in progress, step 1000

Browse files
Files changed (9) hide show
  1. added_tokens.json +1 -2
  2. config.json +10 -1
  3. preprocessor_config.json +0 -0
  4. pytorch_model.bin +1 -1
  5. special_tokens_map.json +2 -2
  6. tokenizer.json +0 -0
  7. tokenizer_config.json +2 -3
  8. training_args.bin +2 -2
  9. vocab.json +0 -0
added_tokens.json CHANGED
@@ -17,7 +17,6 @@
17
  "<|da|>": 50285,
18
  "<|de|>": 50261,
19
  "<|el|>": 50281,
20
- "<|endoftext|>": 50257,
21
  "<|en|>": 50259,
22
  "<|es|>": 50262,
23
  "<|et|>": 50307,
@@ -30,6 +29,7 @@
30
  "<|gu|>": 50333,
31
  "<|haw|>": 50352,
32
  "<|ha|>": 50354,
 
33
  "<|hi|>": 50276,
34
  "<|hr|>": 50291,
35
  "<|ht|>": 50339,
@@ -38,7 +38,6 @@
38
  "<|id|>": 50275,
39
  "<|is|>": 50311,
40
  "<|it|>": 50274,
41
- "<|iw|>": 50279,
42
  "<|ja|>": 50266,
43
  "<|jw|>": 50356,
44
  "<|ka|>": 50329,
 
17
  "<|da|>": 50285,
18
  "<|de|>": 50261,
19
  "<|el|>": 50281,
 
20
  "<|en|>": 50259,
21
  "<|es|>": 50262,
22
  "<|et|>": 50307,
 
29
  "<|gu|>": 50333,
30
  "<|haw|>": 50352,
31
  "<|ha|>": 50354,
32
+ "<|he|>": 50279,
33
  "<|hi|>": 50276,
34
  "<|hr|>": 50291,
35
  "<|ht|>": 50339,
 
38
  "<|id|>": 50275,
39
  "<|is|>": 50311,
40
  "<|it|>": 50274,
 
41
  "<|ja|>": 50266,
42
  "<|jw|>": 50356,
43
  "<|ka|>": 50329,
config.json CHANGED
@@ -2,6 +2,7 @@
2
  "_name_or_path": "openai/whisper-medium",
3
  "activation_dropout": 0.0,
4
  "activation_function": "gelu",
 
5
  "architectures": [
6
  "WhisperForConditionalGeneration"
7
  ],
@@ -11,6 +12,7 @@
11
  50257
12
  ],
13
  "bos_token_id": 50257,
 
14
  "d_model": 1024,
15
  "decoder_attention_heads": 16,
16
  "decoder_ffn_dim": 4096,
@@ -26,6 +28,12 @@
26
  "forced_decoder_ids": null,
27
  "init_std": 0.02,
28
  "is_encoder_decoder": true,
 
 
 
 
 
 
29
  "max_length": 448,
30
  "max_source_positions": 1500,
31
  "max_target_positions": 448,
@@ -35,7 +43,8 @@
35
  "pad_token_id": 50257,
36
  "scale_embedding": false,
37
  "torch_dtype": "float32",
38
- "transformers_version": "4.25.1",
39
  "use_cache": false,
 
40
  "vocab_size": 51865
41
  }
 
2
  "_name_or_path": "openai/whisper-medium",
3
  "activation_dropout": 0.0,
4
  "activation_function": "gelu",
5
+ "apply_spec_augment": false,
6
  "architectures": [
7
  "WhisperForConditionalGeneration"
8
  ],
 
12
  50257
13
  ],
14
  "bos_token_id": 50257,
15
+ "classifier_proj_size": 256,
16
  "d_model": 1024,
17
  "decoder_attention_heads": 16,
18
  "decoder_ffn_dim": 4096,
 
28
  "forced_decoder_ids": null,
29
  "init_std": 0.02,
30
  "is_encoder_decoder": true,
31
+ "mask_feature_length": 10,
32
+ "mask_feature_min_masks": 0,
33
+ "mask_feature_prob": 0.0,
34
+ "mask_time_length": 10,
35
+ "mask_time_min_masks": 2,
36
+ "mask_time_prob": 0.05,
37
  "max_length": 448,
38
  "max_source_positions": 1500,
39
  "max_target_positions": 448,
 
43
  "pad_token_id": 50257,
44
  "scale_embedding": false,
45
  "torch_dtype": "float32",
46
+ "transformers_version": "4.28.1",
47
  "use_cache": false,
48
+ "use_weighted_layer_sum": false,
49
  "vocab_size": 51865
50
  }
preprocessor_config.json CHANGED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:33d3c3938b1083743b88afb8d39125712b4b8743a8fdc286e85b9d04f373ae4e
3
  size 3055754841
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e8d700a26018287c6e2007bc121be050e558a95942ae3bff84a579979433533
3
  size 3055754841
special_tokens_map.json CHANGED
@@ -22,7 +22,7 @@
22
  "<|hi|>",
23
  "<|fi|>",
24
  "<|vi|>",
25
- "<|iw|>",
26
  "<|uk|>",
27
  "<|el|>",
28
  "<|ms|>",
@@ -124,7 +124,7 @@
124
  },
125
  "pad_token": "<|endoftext|>",
126
  "unk_token": {
127
- "content": "",
128
  "lstrip": false,
129
  "normalized": true,
130
  "rstrip": false,
 
22
  "<|hi|>",
23
  "<|fi|>",
24
  "<|vi|>",
25
+ "<|he|>",
26
  "<|uk|>",
27
  "<|el|>",
28
  "<|ms|>",
 
124
  },
125
  "pad_token": "<|endoftext|>",
126
  "unk_token": {
127
+ "content": "<|endoftext|>",
128
  "lstrip": false,
129
  "normalized": true,
130
  "rstrip": false,
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -9,6 +9,7 @@
9
  "rstrip": false,
10
  "single_word": false
11
  },
 
12
  "eos_token": {
13
  "__type": "AddedToken",
14
  "content": "<|endoftext|>",
@@ -19,15 +20,13 @@
19
  },
20
  "errors": "replace",
21
  "model_max_length": 1024,
22
- "name_or_path": "openai/whisper-medium",
23
  "pad_token": null,
24
  "processor_class": "WhisperProcessor",
25
  "return_attention_mask": false,
26
- "special_tokens_map_file": null,
27
  "tokenizer_class": "WhisperTokenizer",
28
  "unk_token": {
29
  "__type": "AddedToken",
30
- "content": "",
31
  "lstrip": false,
32
  "normalized": true,
33
  "rstrip": false,
 
9
  "rstrip": false,
10
  "single_word": false
11
  },
12
+ "clean_up_tokenization_spaces": true,
13
  "eos_token": {
14
  "__type": "AddedToken",
15
  "content": "<|endoftext|>",
 
20
  },
21
  "errors": "replace",
22
  "model_max_length": 1024,
 
23
  "pad_token": null,
24
  "processor_class": "WhisperProcessor",
25
  "return_attention_mask": false,
 
26
  "tokenizer_class": "WhisperTokenizer",
27
  "unk_token": {
28
  "__type": "AddedToken",
29
+ "content": "<|endoftext|>",
30
  "lstrip": false,
31
  "normalized": true,
32
  "rstrip": false,
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:53d44dae25c0d352812e85c24f38a835fab2b1e3f5edb44d6b95848b98afe05c
3
- size 3707
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:473b98d2a30e19958749dfa43771830b95492e4b465cfe7f1c3ad9692485d2ec
3
+ size 3899
vocab.json CHANGED
The diff for this file is too large to render. See raw diff