ptah23 commited on
Commit
38e5092
1 Parent(s): 2db6cb5

End of training

Browse files
.ipynb_checkpoints/README-checkpoint.md ADDED
@@ -0,0 +1,85 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - dv
4
+ license: apache-2.0
5
+ base_model: openai/whisper-small
6
+ tags:
7
+ - generated_from_trainer
8
+ datasets:
9
+ - mozilla-foundation/common_voice_13_0
10
+ metrics:
11
+ - wer
12
+ model-index:
13
+ - name: Whisper Small Dv - Peter Gelderbloem
14
+ results:
15
+ - task:
16
+ name: Automatic Speech Recognition
17
+ type: automatic-speech-recognition
18
+ dataset:
19
+ name: Common Voice 13
20
+ type: mozilla-foundation/common_voice_13_0
21
+ config: dv
22
+ split: None
23
+ metrics:
24
+ - name: Wer
25
+ type: wer
26
+ value: 11.249434920193343
27
+ ---
28
+
29
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
30
+ should probably proofread and complete it, then remove this comment. -->
31
+
32
+ # Whisper Small Dv - Peter Gelderbloem
33
+
34
+ This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Common Voice 13 dataset.
35
+ It achieves the following results on the evaluation set:
36
+ - Loss: 0.2863
37
+ - Wer Ortho: 57.7129
38
+ - Wer: 11.2494
39
+
40
+ ## Model description
41
+
42
+ More information needed
43
+
44
+ ## Intended uses & limitations
45
+
46
+ More information needed
47
+
48
+ ## Training and evaluation data
49
+
50
+ More information needed
51
+
52
+ ## Training procedure
53
+
54
+ ### Training hyperparameters
55
+
56
+ The following hyperparameters were used during training:
57
+ - learning_rate: 1e-05
58
+ - train_batch_size: 16
59
+ - eval_batch_size: 16
60
+ - seed: 42
61
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
62
+ - lr_scheduler_type: constant_with_warmup
63
+ - lr_scheduler_warmup_steps: 50
64
+ - training_steps: 4000
65
+
66
+ ### Training results
67
+
68
+ | Training Loss | Epoch | Step | Validation Loss | Wer | Wer Ortho |
69
+ |:-------------:|:-----:|:----:|:---------------:|:-------:|:---------:|
70
+ | 0.1248 | 1.63 | 500 | 0.1684 | 12.9881 | 62.0447 |
71
+ | 0.0484 | 3.26 | 1000 | 0.1629 | 11.6493 | 58.6113 |
72
+ | 0.0315 | 4.89 | 1500 | 0.1878 | 11.7224 | 58.9386 |
73
+ | 0.0125 | 6.51 | 2000 | 0.2308 | 11.0895 | 57.2185 |
74
+ | 0.0058 | 8.14 | 2500 | 0.2671 | 11.0773 | 57.6224 |
75
+ | 0.0049 | 9.77 | 3000 | 0.2843 | 11.2564 | 57.6572 |
76
+ | 0.0033 | 11.4 | 3500 | 0.2845 | 11.0982 | 57.1558 |
77
+ | 0.0046 | 13.03 | 4000 | 0.2863 | 57.7129 | 11.2494 |
78
+
79
+
80
+ ### Framework versions
81
+
82
+ - Transformers 4.31.0.dev0
83
+ - Pytorch 1.12.1+cu116
84
+ - Datasets 2.4.0
85
+ - Tokenizers 0.12.1
.ipynb_checkpoints/config-checkpoint.json ADDED
@@ -0,0 +1,152 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "WhisperForConditionalGeneration"
8
+ ],
9
+ "attention_dropout": 0.0,
10
+ "begin_suppress_tokens": [
11
+ 220,
12
+ 50257
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": [
29
+ [
30
+ 1,
31
+ 50259
32
+ ],
33
+ [
34
+ 2,
35
+ 50359
36
+ ],
37
+ [
38
+ 3,
39
+ 50363
40
+ ]
41
+ ],
42
+ "init_std": 0.02,
43
+ "is_encoder_decoder": true,
44
+ "mask_feature_length": 10,
45
+ "mask_feature_min_masks": 0,
46
+ "mask_feature_prob": 0.0,
47
+ "mask_time_length": 10,
48
+ "mask_time_min_masks": 2,
49
+ "mask_time_prob": 0.05,
50
+ "max_length": 448,
51
+ "max_source_positions": 1500,
52
+ "max_target_positions": 448,
53
+ "median_filter_width": 7,
54
+ "model_type": "whisper",
55
+ "num_hidden_layers": 12,
56
+ "num_mel_bins": 80,
57
+ "pad_token_id": 50257,
58
+ "scale_embedding": false,
59
+ "suppress_tokens": [
60
+ 1,
61
+ 2,
62
+ 7,
63
+ 8,
64
+ 9,
65
+ 10,
66
+ 14,
67
+ 25,
68
+ 26,
69
+ 27,
70
+ 28,
71
+ 29,
72
+ 31,
73
+ 58,
74
+ 59,
75
+ 60,
76
+ 61,
77
+ 62,
78
+ 63,
79
+ 90,
80
+ 91,
81
+ 92,
82
+ 93,
83
+ 359,
84
+ 503,
85
+ 522,
86
+ 542,
87
+ 873,
88
+ 893,
89
+ 902,
90
+ 918,
91
+ 922,
92
+ 931,
93
+ 1350,
94
+ 1853,
95
+ 1982,
96
+ 2460,
97
+ 2627,
98
+ 3246,
99
+ 3253,
100
+ 3268,
101
+ 3536,
102
+ 3846,
103
+ 3961,
104
+ 4183,
105
+ 4667,
106
+ 6585,
107
+ 6647,
108
+ 7273,
109
+ 9061,
110
+ 9383,
111
+ 10428,
112
+ 10929,
113
+ 11938,
114
+ 12033,
115
+ 12331,
116
+ 12562,
117
+ 13793,
118
+ 14157,
119
+ 14635,
120
+ 15265,
121
+ 15618,
122
+ 16553,
123
+ 16604,
124
+ 18362,
125
+ 18956,
126
+ 20075,
127
+ 21675,
128
+ 22520,
129
+ 26130,
130
+ 26161,
131
+ 26435,
132
+ 28279,
133
+ 29464,
134
+ 31650,
135
+ 32302,
136
+ 32470,
137
+ 36865,
138
+ 42863,
139
+ 47425,
140
+ 49870,
141
+ 50254,
142
+ 50258,
143
+ 50360,
144
+ 50361,
145
+ 50362
146
+ ],
147
+ "torch_dtype": "float32",
148
+ "transformers_version": "4.31.0.dev0",
149
+ "use_cache": false,
150
+ "use_weighted_layer_sum": false,
151
+ "vocab_size": 51865
152
+ }
README.md CHANGED
@@ -18,7 +18,7 @@ model-index:
18
  dataset:
19
  name: Common Voice 13
20
  type: mozilla-foundation/common_voice_13_0
21
- config: null
22
  split: None
23
  metrics:
24
  - name: Wer
 
18
  dataset:
19
  name: Common Voice 13
20
  type: mozilla-foundation/common_voice_13_0
21
+ config: dv
22
  split: None
23
  metrics:
24
  - name: Wer