Hugging Face's logo

mlmarian
/
whisper-finetuning

TensorBoard
Safetensors
whisper
Model card Files
xet
 Metrics Community
mlmarian commited on
Commit
be350ff
·
verified ·
1 Parent(s): 6091ccd

Training in progress, epoch 1

Browse files
Files changed (8) hide show
  1. config.json +79 -0
  2. generation_config.json +96 -0
  3. model.safetensors +3 -0
  4. preprocessor_config.json +14 -0
  5. runs/Sep19_10-52-29_3a1e3428f2e8/events.out.tfevents.1726743152.3a1e3428f2e8.726.0 +3 -0
  6. runs/Sep19_10-58-42_3a1e3428f2e8/events.out.tfevents.1726743526.3a1e3428f2e8.726.1 +3 -0
  7. runs/Sep19_11-14-43_3a1e3428f2e8/events.out.tfevents.1726744486.3a1e3428f2e8.726.2 +3 -0
  8. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,79 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "openai/whisper-small",
3
+ "activation_dropout": 0.0,
4
+ "activation_function": "gelu",
5
+ "apply_spec_augment": false,
6
+ "architectures": [
7
+ "WhisperForAudioClassification"
8
+ ],
9
+ "attention_dropout": 0.0,
10
+ "bos_token_id": 50257,
11
+ "classifier_proj_size": 256,
12
+ "d_model": 768,
13
+ "decoder_attention_heads": 12,
14
+ "decoder_ffn_dim": 3072,
15
+ "decoder_layerdrop": 0.0,
16
+ "decoder_layers": 12,
17
+ "decoder_start_token_id": 50258,
18
+ "dropout": 0.0,
19
+ "encoder_attention_heads": 12,
20
+ "encoder_ffn_dim": 3072,
21
+ "encoder_layerdrop": 0.0,
22
+ "encoder_layers": 12,
23
+ "eos_token_id": 50257,
24
+ "forced_decoder_ids": [
25
+ [
26
+ 1,
27
+ 50259
28
+ ],
29
+ [
30
+ 2,
31
+ 50359
32
+ ],
33
+ [
34
+ 3,
35
+ 50363
36
+ ]
37
+ ],
38
+ "id2label": {
39
+ "0": "teens",
40
+ "1": "twenties",
41
+ "2": "thirties",
42
+ "3": "fourties",
43
+ "4": "fifties",
44
+ "5": "sixties",
45
+ "6": "seventies",
46
+ "7": "eighties"
47
+ },
48
+ "init_std": 0.02,
49
+ "is_encoder_decoder": true,
50
+ "label2id": {
51
+ "eighties": "7",
52
+ "fifties": "4",
53
+ "fourties": "3",
54
+ "seventies": "6",
55
+ "sixties": "5",
56
+ "teens": "0",
57
+ "thirties": "2",
58
+ "twenties": "1"
59
+ },
60
+ "mask_feature_length": 10,
61
+ "mask_feature_min_masks": 0,
62
+ "mask_feature_prob": 0.0,
63
+ "mask_time_length": 10,
64
+ "mask_time_min_masks": 2,
65
+ "mask_time_prob": 0.05,
66
+ "max_source_positions": 1500,
67
+ "max_target_positions": 448,
68
+ "median_filter_width": 7,
69
+ "model_type": "whisper",
70
+ "num_hidden_layers": 12,
71
+ "num_mel_bins": 80,
72
+ "pad_token_id": 50257,
73
+ "scale_embedding": false,
74
+ "torch_dtype": "float32",
75
+ "transformers_version": "4.45.0.dev0",
76
+ "use_cache": true,
77
+ "use_weighted_layer_sum": false,
78
+ "vocab_size": 51865
79
+ }
generation_config.json ADDED
@@ -0,0 +1,96 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "begin_suppress_tokens": [
3
+ 220,
4
+ 50257
5
+ ],
6
+ "max_length": 448,
7
+ "suppress_tokens": [
8
+ 1,
9
+ 2,
10
+ 7,
11
+ 8,
12
+ 9,
13
+ 10,
14
+ 14,
15
+ 25,
16
+ 26,
17
+ 27,
18
+ 28,
19
+ 29,
20
+ 31,
21
+ 58,
22
+ 59,
23
+ 60,
24
+ 61,
25
+ 62,
26
+ 63,
27
+ 90,
28
+ 91,
29
+ 92,
30
+ 93,
31
+ 359,
32
+ 503,
33
+ 522,
34
+ 542,
35
+ 873,
36
+ 893,
37
+ 902,
38
+ 918,
39
+ 922,
40
+ 931,
41
+ 1350,
42
+ 1853,
43
+ 1982,
44
+ 2460,
45
+ 2627,
46
+ 3246,
47
+ 3253,
48
+ 3268,
49
+ 3536,
50
+ 3846,
51
+ 3961,
52
+ 4183,
53
+ 4667,
54
+ 6585,
55
+ 6647,
56
+ 7273,
57
+ 9061,
58
+ 9383,
59
+ 10428,
60
+ 10929,
61
+ 11938,
62
+ 12033,
63
+ 12331,
64
+ 12562,
65
+ 13793,
66
+ 14157,
67
+ 14635,
68
+ 15265,
69
+ 15618,
70
+ 16553,
71
+ 16604,
72
+ 18362,
73
+ 18956,
74
+ 20075,
75
+ 21675,
76
+ 22520,
77
+ 26130,
78
+ 26161,
79
+ 26435,
80
+ 28279,
81
+ 29464,
82
+ 31650,
83
+ 32302,
84
+ 32470,
85
+ 36865,
86
+ 42863,
87
+ 47425,
88
+ 49870,
89
+ 50254,
90
+ 50258,
91
+ 50360,
92
+ 50361,
93
+ 50362
94
+ ],
95
+ "transformers_version": "4.45.0.dev0"
96
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5460e55a8fde299ed277124efdccbe5f1fe9767ecb3da6e890c92ee15956fea4
3
+ size 353432528
preprocessor_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "chunk_length": 30,
3
+ "feature_extractor_type": "WhisperFeatureExtractor",
4
+ "feature_size": 80,
5
+ "hop_length": 160,
6
+ "n_fft": 400,
7
+ "n_samples": 480000,
8
+ "nb_max_frames": 3000,
9
+ "padding_side": "right",
10
+ "padding_value": 0.0,
11
+ "processor_class": "WhisperProcessor",
12
+ "return_attention_mask": false,
13
+ "sampling_rate": 16000
14
+ }
runs/Sep19_10-52-29_3a1e3428f2e8/events.out.tfevents.1726743152.3a1e3428f2e8.726.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa1fae2ede473de4e62e1418861bc9e45733b64f3b8cf0ab4fb660e7d65e7930
3
+ size 64650
runs/Sep19_10-58-42_3a1e3428f2e8/events.out.tfevents.1726743526.3a1e3428f2e8.726.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f993b37f768018004312cacc11a43db7901a8bbb6c0c9646a0ca181cabc7eadb
3
+ size 65168
runs/Sep19_11-14-43_3a1e3428f2e8/events.out.tfevents.1726744486.3a1e3428f2e8.726.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67a5fed9cdf6d63a6560b1851ae96477762d028982dbe4a1ce5fd142ee657b63
3
+ size 64655
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b93eefa2adeafa8717668a4629be5da2697f088539b49ae2f9332373619c009
3
+ size 5304