Hugging Face's logo

w11wo
/
wav2vec2-xls-r-300m-zh-HK-v2

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
wav2vec2
Generated from Trainer
hf-asr-leaderboard
robust-speech-event
Eval Results
Inference Endpoints
Model card Files Metrics Community
w11wo commited on
Commit
5679ecf
·
1 Parent(s): ace94fa

update model card README.md

Browse files
Files changed (2) hide show
  1. README.md +137 -0
  2. nohup.out +18 -0
README.md ADDED
@@ -0,0 +1,137 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ datasets:
6
+ - common_voice
7
+ model-index:
8
+ - name: ''
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ #
16
+
17
+ This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the common_voice dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 0.8086
20
+ - Wer: 1.2451
21
+ - Cer: 0.3156
22
+
23
+ ## Model description
24
+
25
+ More information needed
26
+
27
+ ## Intended uses & limitations
28
+
29
+ More information needed
30
+
31
+ ## Training and evaluation data
32
+
33
+ More information needed
34
+
35
+ ## Training procedure
36
+
37
+ ### Training hyperparameters
38
+
39
+ The following hyperparameters were used during training:
40
+ - learning_rate: 0.0001
41
+ - train_batch_size: 8
42
+ - eval_batch_size: 8
43
+ - seed: 42
44
+ - gradient_accumulation_steps: 4
45
+ - total_train_batch_size: 32
46
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
+ - lr_scheduler_type: linear
48
+ - lr_scheduler_warmup_steps: 2000
49
+ - num_epochs: 100.0
50
+ - mixed_precision_training: Native AMP
51
+
52
+ ### Training results
53
+
54
+ | Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
55
+ |:-------------:|:-----:|:-----:|:---------------:|:------:|:------:|
56
+ | 69.8341 | 1.34 | 500 | 80.0722 | 1.0 | 1.0 |
57
+ | 6.6418 | 2.68 | 1000 | 6.6346 | 1.0 | 1.0 |
58
+ | 6.2419 | 4.02 | 1500 | 6.2909 | 1.0 | 1.0 |
59
+ | 6.0813 | 5.36 | 2000 | 6.1150 | 1.0 | 1.0 |
60
+ | 5.9677 | 6.7 | 2500 | 6.0301 | 1.1386 | 1.0028 |
61
+ | 5.9296 | 8.04 | 3000 | 5.8975 | 1.2113 | 1.0058 |
62
+ | 5.6434 | 9.38 | 3500 | 5.5404 | 2.1624 | 1.0171 |
63
+ | 5.1974 | 10.72 | 4000 | 4.5440 | 2.1702 | 0.9366 |
64
+ | 4.3601 | 12.06 | 4500 | 3.3839 | 2.2464 | 0.8998 |
65
+ | 3.9321 | 13.4 | 5000 | 2.8785 | 2.3097 | 0.8400 |
66
+ | 3.6462 | 14.74 | 5500 | 2.5108 | 1.9623 | 0.6663 |
67
+ | 3.5156 | 16.09 | 6000 | 2.2790 | 1.6479 | 0.5706 |
68
+ | 3.32 | 17.43 | 6500 | 2.1450 | 1.8337 | 0.6244 |
69
+ | 3.1918 | 18.77 | 7000 | 1.8536 | 1.9394 | 0.6017 |
70
+ | 3.1139 | 20.11 | 7500 | 1.7205 | 1.9112 | 0.5638 |
71
+ | 2.8995 | 21.45 | 8000 | 1.5478 | 1.0624 | 0.3250 |
72
+ | 2.7572 | 22.79 | 8500 | 1.4068 | 1.1412 | 0.3367 |
73
+ | 2.6881 | 24.13 | 9000 | 1.3312 | 2.0100 | 0.5683 |
74
+ | 2.5993 | 25.47 | 9500 | 1.2553 | 2.0039 | 0.6450 |
75
+ | 2.5304 | 26.81 | 10000 | 1.2422 | 2.0394 | 0.5789 |
76
+ | 2.4352 | 28.15 | 10500 | 1.1582 | 1.9970 | 0.5507 |
77
+ | 2.3795 | 29.49 | 11000 | 1.1160 | 1.8255 | 0.4844 |
78
+ | 2.3287 | 30.83 | 11500 | 1.0775 | 1.4123 | 0.3780 |
79
+ | 2.2622 | 32.17 | 12000 | 1.0704 | 1.7445 | 0.4894 |
80
+ | 2.2225 | 33.51 | 12500 | 1.0272 | 1.7237 | 0.5058 |
81
+ | 2.1843 | 34.85 | 13000 | 0.9756 | 1.8042 | 0.5028 |
82
+ | 2.1 | 36.19 | 13500 | 0.9527 | 1.8909 | 0.6055 |
83
+ | 2.0741 | 37.53 | 14000 | 0.9418 | 1.9026 | 0.5880 |
84
+ | 2.0179 | 38.87 | 14500 | 0.9363 | 1.7977 | 0.5246 |
85
+ | 2.0615 | 40.21 | 15000 | 0.9635 | 1.8112 | 0.5599 |
86
+ | 1.9448 | 41.55 | 15500 | 0.9249 | 1.7250 | 0.4914 |
87
+ | 1.8966 | 42.89 | 16000 | 0.9023 | 1.5829 | 0.4319 |
88
+ | 1.8662 | 44.24 | 16500 | 0.9002 | 1.4833 | 0.4230 |
89
+ | 1.8136 | 45.58 | 17000 | 0.9076 | 1.1828 | 0.2987 |
90
+ | 1.7908 | 46.92 | 17500 | 0.8774 | 1.5773 | 0.4258 |
91
+ | 1.7354 | 48.26 | 18000 | 0.8727 | 1.5037 | 0.4024 |
92
+ | 1.6739 | 49.6 | 18500 | 0.8636 | 1.1239 | 0.2789 |
93
+ | 1.6457 | 50.94 | 19000 | 0.8516 | 1.2269 | 0.3104 |
94
+ | 1.5847 | 52.28 | 19500 | 0.8399 | 1.3309 | 0.3360 |
95
+ | 1.5971 | 53.62 | 20000 | 0.8441 | 1.3153 | 0.3335 |
96
+ | 1.602 | 54.96 | 20500 | 0.8590 | 1.2932 | 0.3433 |
97
+ | 1.5063 | 56.3 | 21000 | 0.8334 | 1.1312 | 0.2875 |
98
+ | 1.4631 | 57.64 | 21500 | 0.8474 | 1.1698 | 0.2999 |
99
+ | 1.4997 | 58.98 | 22000 | 0.8638 | 1.4279 | 0.3854 |
100
+ | 1.4301 | 60.32 | 22500 | 0.8550 | 1.2737 | 0.3300 |
101
+ | 1.3798 | 61.66 | 23000 | 0.8266 | 1.1802 | 0.2934 |
102
+ | 1.3454 | 63.0 | 23500 | 0.8235 | 1.3816 | 0.3711 |
103
+ | 1.3678 | 64.34 | 24000 | 0.8550 | 1.6427 | 0.5035 |
104
+ | 1.3761 | 65.68 | 24500 | 0.8510 | 1.6709 | 0.4907 |
105
+ | 1.2668 | 67.02 | 25000 | 0.8515 | 1.5842 | 0.4505 |
106
+ | 1.2835 | 68.36 | 25500 | 0.8283 | 1.5353 | 0.4221 |
107
+ | 1.2961 | 69.7 | 26000 | 0.8339 | 1.5743 | 0.4369 |
108
+ | 1.2656 | 71.05 | 26500 | 0.8331 | 1.5331 | 0.4217 |
109
+ | 1.2556 | 72.39 | 27000 | 0.8242 | 1.4708 | 0.4109 |
110
+ | 1.2043 | 73.73 | 27500 | 0.8245 | 1.4469 | 0.4031 |
111
+ | 1.2722 | 75.07 | 28000 | 0.8202 | 1.4924 | 0.4096 |
112
+ | 1.202 | 76.41 | 28500 | 0.8290 | 1.3807 | 0.3719 |
113
+ | 1.1679 | 77.75 | 29000 | 0.8195 | 1.4097 | 0.3749 |
114
+ | 1.1967 | 79.09 | 29500 | 0.8059 | 1.2074 | 0.3077 |
115
+ | 1.1241 | 80.43 | 30000 | 0.8137 | 1.2451 | 0.3270 |
116
+ | 1.1414 | 81.77 | 30500 | 0.8117 | 1.2031 | 0.3121 |
117
+ | 1.132 | 83.11 | 31000 | 0.8234 | 1.4266 | 0.3901 |
118
+ | 1.0982 | 84.45 | 31500 | 0.8064 | 1.3712 | 0.3607 |
119
+ | 1.0797 | 85.79 | 32000 | 0.8167 | 1.3356 | 0.3562 |
120
+ | 1.0119 | 87.13 | 32500 | 0.8215 | 1.2754 | 0.3268 |
121
+ | 1.0216 | 88.47 | 33000 | 0.8163 | 1.2512 | 0.3184 |
122
+ | 1.0375 | 89.81 | 33500 | 0.8137 | 1.2685 | 0.3290 |
123
+ | 0.9794 | 91.15 | 34000 | 0.8220 | 1.2724 | 0.3255 |
124
+ | 1.0207 | 92.49 | 34500 | 0.8165 | 1.2906 | 0.3361 |
125
+ | 1.0169 | 93.83 | 35000 | 0.8153 | 1.2819 | 0.3305 |
126
+ | 1.0127 | 95.17 | 35500 | 0.8187 | 1.2832 | 0.3252 |
127
+ | 0.9978 | 96.51 | 36000 | 0.8111 | 1.2612 | 0.3210 |
128
+ | 0.9923 | 97.85 | 36500 | 0.8076 | 1.2278 | 0.3122 |
129
+ | 1.0451 | 99.2 | 37000 | 0.8086 | 1.2451 | 0.3156 |
130
+
131
+
132
+ ### Framework versions
133
+
134
+ - Transformers 4.17.0.dev0
135
+ - Pytorch 1.10.2+cu102
136
+ - Datasets 1.18.4.dev0
137
+ - Tokenizers 0.11.0
nohup.out CHANGED
@@ -23221,3 +23221,21 @@ Saving model checkpoint to ./
23221
  Configuration saved in ./config.json
23222
  Model weights saved in ./pytorch_model.bin
23223
  Configuration saved in ./preprocessor_config.json
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
23221
  Configuration saved in ./config.json
23222
  Model weights saved in ./pytorch_model.bin
23223
  Configuration saved in ./preprocessor_config.json
23224
+ {'eval_loss': 0.8086187243461609, 'eval_wer': 1.2451277609354698, 'eval_cer': 0.3155884893394554, 'eval_runtime': 119.7199, 'eval_samples_per_second': 19.228, 'eval_steps_per_second': 2.406, 'epoch': 99.2}
23225
+ {'loss': 1.0189, 'learning_rate': 6.203966005665723e-07, 'epoch': 99.46}
23226
+ {'loss': 0.9878, 'learning_rate': 3.371104815864023e-07, 'epoch': 99.73}
23227
+ {'loss': 0.96, 'learning_rate': 5.3824362606232296e-08, 'epoch': 100.0}
23228
+ {'train_runtime': 72640.1075, 'train_samples_per_second': 16.45, 'train_steps_per_second': 0.513, 'train_loss': 3.7852419735087786, 'epoch': 100.0}
23229
+
23230
+
23231
+ 52f4175..ace94fa main -> main
23232
+
23233
+ 02/07/2022 12:45:51 - WARNING - huggingface_hub.repository - To https://huggingface.co/w11wo/wav2vec2-xls-r-300m-zh-HK-v2
23234
+ 52f4175..ace94fa main -> main
23235
+
23236
+
23237
+
23238
+
23239
+
23240
+ Dropping the following result as it does not have all the necessary fields:
23241
+ {'dataset': {'name': 'common_voice', 'type': 'common_voice', 'args': 'zh-HK'}}