LightFury9 commited on
Commit
4d60466
1 Parent(s): 1313120

End of training

Browse files
README.md ADDED
@@ -0,0 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - en
4
+ license: apache-2.0
5
+ base_model: openai/whisper-tiny
6
+ tags:
7
+ - generated_from_trainer
8
+ metrics:
9
+ - wer
10
+ model-index:
11
+ - name: whisper_tiny-mini2
12
+ results: []
13
+ ---
14
+
15
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
16
+ should probably proofread and complete it, then remove this comment. -->
17
+
18
+ # whisper_tiny-mini2
19
+
20
+ This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the None dataset.
21
+ It achieves the following results on the evaluation set:
22
+ - Loss: 0.1008
23
+ - Wer: 5.5449
24
+
25
+ ## Model description
26
+
27
+ More information needed
28
+
29
+ ## Intended uses & limitations
30
+
31
+ More information needed
32
+
33
+ ## Training and evaluation data
34
+
35
+ More information needed
36
+
37
+ ## Training procedure
38
+
39
+ ### Training hyperparameters
40
+
41
+ The following hyperparameters were used during training:
42
+ - learning_rate: 1e-05
43
+ - train_batch_size: 16
44
+ - eval_batch_size: 8
45
+ - seed: 42
46
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
+ - lr_scheduler_type: linear
48
+ - lr_scheduler_warmup_steps: 100
49
+ - training_steps: 1000
50
+ - mixed_precision_training: Native AMP
51
+
52
+ ### Training results
53
+
54
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
55
+ |:-------------:|:-----:|:----:|:---------------:|:-------:|
56
+ | 2.0118 | 1.49 | 100 | 1.8148 | 15.4876 |
57
+ | 0.3222 | 2.99 | 200 | 0.3016 | 8.0306 |
58
+ | 0.0315 | 4.48 | 300 | 0.1206 | 4.7801 |
59
+ | 0.0098 | 5.97 | 400 | 0.1097 | 4.7801 |
60
+ | 0.0025 | 7.46 | 500 | 0.1024 | 5.3537 |
61
+ | 0.0017 | 8.96 | 600 | 0.1044 | 5.1625 |
62
+ | 0.0011 | 10.45 | 700 | 0.1033 | 4.7801 |
63
+ | 0.001 | 11.94 | 800 | 0.1013 | 5.5449 |
64
+ | 0.0008 | 13.43 | 900 | 0.1009 | 5.3537 |
65
+ | 0.0008 | 14.93 | 1000 | 0.1008 | 5.5449 |
66
+
67
+
68
+ ### Framework versions
69
+
70
+ - Transformers 4.35.2
71
+ - Pytorch 2.1.0+cu118
72
+ - Datasets 2.15.0
73
+ - Tokenizers 0.15.0
config.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "openai/whisper-tiny.en",
3
+ "activation_dropout": 0.0,
4
+ "activation_function": "gelu",
5
+ "apply_spec_augment": false,
6
+ "architectures": [
7
+ "WhisperForConditionalGeneration"
8
+ ],
9
+ "attention_dropout": 0.0,
10
+ "begin_suppress_tokens": [
11
+ 220,
12
+ 50256
13
+ ],
14
+ "bos_token_id": 50257,
15
+ "classifier_proj_size": 256,
16
+ "d_model": 384,
17
+ "decoder_attention_heads": 6,
18
+ "decoder_ffn_dim": 1536,
19
+ "decoder_layerdrop": 0.0,
20
+ "decoder_layers": 4,
21
+ "decoder_start_token_id": 50257,
22
+ "dropout": 0.0,
23
+ "encoder_attention_heads": 6,
24
+ "encoder_ffn_dim": 1536,
25
+ "encoder_layerdrop": 0.0,
26
+ "encoder_layers": 4,
27
+ "eos_token_id": 50256,
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,
40
+ "median_filter_width": 7,
41
+ "model_type": "whisper",
42
+ "num_hidden_layers": 4,
43
+ "num_mel_bins": 80,
44
+ "pad_token_id": 50256,
45
+ "scale_embedding": false,
46
+ "suppress_tokens": [],
47
+ "torch_dtype": "float32",
48
+ "transformers_version": "4.35.2",
49
+ "use_cache": true,
50
+ "use_weighted_layer_sum": false,
51
+ "vocab_size": 51864
52
+ }
generation_config.json ADDED
@@ -0,0 +1,148 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alignment_heads": [
3
+ [
4
+ 1,
5
+ 0
6
+ ],
7
+ [
8
+ 2,
9
+ 0
10
+ ],
11
+ [
12
+ 2,
13
+ 5
14
+ ],
15
+ [
16
+ 3,
17
+ 0
18
+ ],
19
+ [
20
+ 3,
21
+ 1
22
+ ],
23
+ [
24
+ 3,
25
+ 2
26
+ ],
27
+ [
28
+ 3,
29
+ 3
30
+ ],
31
+ [
32
+ 3,
33
+ 4
34
+ ]
35
+ ],
36
+ "begin_suppress_tokens": [
37
+ 220,
38
+ 50256
39
+ ],
40
+ "bos_token_id": 50257,
41
+ "decoder_start_token_id": 50257,
42
+ "eos_token_id": 50256,
43
+ "forced_decoder_ids": [
44
+ [
45
+ 1,
46
+ 50362
47
+ ]
48
+ ],
49
+ "is_multilingual": false,
50
+ "max_initial_timestamp_index": 1,
51
+ "max_length": 448,
52
+ "no_timestamps_token_id": 50362,
53
+ "pad_token_id": 50256,
54
+ "return_timestamps": false,
55
+ "suppress_tokens": [
56
+ 1,
57
+ 2,
58
+ 7,
59
+ 8,
60
+ 9,
61
+ 10,
62
+ 14,
63
+ 25,
64
+ 26,
65
+ 27,
66
+ 28,
67
+ 29,
68
+ 31,
69
+ 58,
70
+ 59,
71
+ 60,
72
+ 61,
73
+ 62,
74
+ 63,
75
+ 90,
76
+ 91,
77
+ 92,
78
+ 93,
79
+ 357,
80
+ 366,
81
+ 438,
82
+ 532,
83
+ 685,
84
+ 705,
85
+ 796,
86
+ 930,
87
+ 1058,
88
+ 1220,
89
+ 1267,
90
+ 1279,
91
+ 1303,
92
+ 1343,
93
+ 1377,
94
+ 1391,
95
+ 1635,
96
+ 1782,
97
+ 1875,
98
+ 2162,
99
+ 2361,
100
+ 2488,
101
+ 3467,
102
+ 4008,
103
+ 4211,
104
+ 4600,
105
+ 4808,
106
+ 5299,
107
+ 5855,
108
+ 6329,
109
+ 7203,
110
+ 9609,
111
+ 9959,
112
+ 10563,
113
+ 10786,
114
+ 11420,
115
+ 11709,
116
+ 11907,
117
+ 13163,
118
+ 13697,
119
+ 13700,
120
+ 14808,
121
+ 15306,
122
+ 16410,
123
+ 16791,
124
+ 17992,
125
+ 19203,
126
+ 19510,
127
+ 20724,
128
+ 22305,
129
+ 22935,
130
+ 27007,
131
+ 30109,
132
+ 30420,
133
+ 33409,
134
+ 34949,
135
+ 40283,
136
+ 40493,
137
+ 40549,
138
+ 47282,
139
+ 49146,
140
+ 50257,
141
+ 50357,
142
+ 50358,
143
+ 50359,
144
+ 50360,
145
+ 50361
146
+ ],
147
+ "transformers_version": "4.35.2"
148
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:360f20b8f7498170392d248f4cb0681fc18e7d39e750f38f415613587ecc8267
3
+ size 151060136
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/Dec07_09-07-16_897aa6f347fe/events.out.tfevents.1701940041.897aa6f347fe.567.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6fffc057fab4d3d6d75a910600ddea7a87eae8c9ad6b3ae3f99e30ea20f16e4d
3
+ size 14876
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:713ec4e433894717288669474c0d354c46bd3f3fdc31aef09ea1f42ff5be86c1
3
+ size 4728