Hugging Face's logo

xekri
/
mms-common_voice_13_0-eo-1

Automatic Speech Recognition
Transformers
PyTorch
Esperanto
wav2vec2
mozilla-foundation/common_voice_13_0
Generated from Trainer
Inference Endpoints
Model card Files Community
1
xekri commited on
Commit
92e2276
•
1 Parent(s): fc38cbc

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +108 -0
README.md ADDED
@@ -0,0 +1,108 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - generated_from_trainer
4
+ metrics:
5
+ - wer
6
+ model-index:
7
+ - name: mms-common_voice_13_0-eo-1
8
+ results: []
9
+ ---
10
+
11
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
+ should probably proofread and complete it, then remove this comment. -->
13
+
14
+ # mms-common_voice_13_0-eo-1
15
+
16
+ This model is a fine-tuned version of [patrickvonplaten/mms-300m](https://huggingface.co/patrickvonplaten/mms-300m) on the None dataset.
17
+ It achieves the following results on the evaluation set:
18
+ - Loss: 0.2262
19
+ - Cer: 0.0208
20
+ - Wer: 0.0672
21
+
22
+ ## Model description
23
+
24
+ More information needed
25
+
26
+ ## Intended uses & limitations
27
+
28
+ More information needed
29
+
30
+ ## Training and evaluation data
31
+
32
+ More information needed
33
+
34
+ ## Training procedure
35
+
36
+ ### Training hyperparameters
37
+
38
+ The following hyperparameters were used during training:
39
+ - learning_rate: 3e-05
40
+ - train_batch_size: 8
41
+ - eval_batch_size: 8
42
+ - seed: 42
43
+ - gradient_accumulation_steps: 4
44
+ - total_train_batch_size: 32
45
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
+ - lr_scheduler_type: linear
47
+ - lr_scheduler_warmup_steps: 500
48
+ - num_epochs: 100
49
+ - mixed_precision_training: Native AMP
50
+
51
+ ### Training results
52
+
53
+ | Training Loss | Epoch | Step | Cer | Validation Loss | Wer |
54
+ |:-------------:|:-----:|:-----:|:------:|:---------------:|:------:|
55
+ | 2.3129 | 2.13 | 1000 | 0.0580 | 0.5042 | 0.2703 |
56
+ | 0.2251 | 4.27 | 2000 | 0.0295 | 0.1782 | 0.1198 |
57
+ | 0.1462 | 6.4 | 3000 | 0.0265 | 0.1635 | 0.1019 |
58
+ | 0.1162 | 8.53 | 4000 | 0.0248 | 0.1619 | 0.0931 |
59
+ | 0.0988 | 10.67 | 5000 | 0.0249 | 0.1654 | 0.0940 |
60
+ | 0.0904 | 12.8 | 6000 | 0.0242 | 0.1702 | 0.0845 |
61
+ | 0.0813 | 14.93 | 7000 | 0.0239 | 0.1658 | 0.0846 |
62
+ | 0.074 | 17.09 | 8000 | 0.0240 | 0.1763 | 0.0793 |
63
+ | 0.0692 | 19.22 | 9000 | 0.0243 | 0.1768 | 0.0835 |
64
+ | 0.0652 | 21.36 | 10000 | 0.0237 | 0.1812 | 0.0797 |
65
+ | 0.0593 | 23.5 | 11000 | 0.0221 | 0.1810 | 0.0750 |
66
+ | 0.0547 | 25.63 | 12000 | 0.0233 | 0.1835 | 0.0794 |
67
+ | 0.0514 | 27.76 | 13000 | 0.0224 | 0.1828 | 0.0761 |
68
+ | 0.0488 | 29.9 | 14000 | 0.0224 | 0.1844 | 0.0766 |
69
+ | 0.0478 | 32.03 | 15000 | 0.0226 | 0.1910 | 0.0769 |
70
+ | 0.0459 | 34.16 | 16000 | 0.0239 | 0.1965 | 0.0831 |
71
+ | 0.0429 | 36.3 | 17000 | 0.0220 | 0.2000 | 0.0760 |
72
+ | 0.0443 | 38.43 | 18000 | 0.0228 | 0.2039 | 0.0774 |
73
+ | 0.0398 | 40.56 | 19000 | 0.0219 | 0.1981 | 0.0755 |
74
+ | 0.0408 | 42.7 | 20000 | 0.0239 | 0.2053 | 0.0776 |
75
+ | 0.0406 | 44.83 | 21000 | 0.0221 | 0.2050 | 0.0740 |
76
+ | 0.0383 | 46.96 | 22000 | 0.0224 | 0.2128 | 0.0733 |
77
+ | 0.0379 | 49.1 | 23000 | 0.0220 | 0.2110 | 0.0731 |
78
+ | 0.0369 | 51.23 | 24000 | 0.0220 | 0.2145 | 0.0745 |
79
+ | 0.0341 | 53.36 | 25000 | 0.0222 | 0.2146 | 0.0725 |
80
+ | 0.0322 | 55.5 | 26000 | 0.0216 | 0.2130 | 0.0710 |
81
+ | 0.0316 | 57.63 | 27000 | 0.0222 | 0.2134 | 0.0716 |
82
+ | 0.0324 | 59.76 | 28000 | 0.0222 | 0.2172 | 0.0731 |
83
+ | 0.0315 | 61.9 | 29000 | 0.0228 | 0.2207 | 0.0745 |
84
+ | 0.0294 | 64.03 | 30000 | 0.0218 | 0.2183 | 0.0717 |
85
+ | 0.028 | 66.16 | 31000 | 0.0214 | 0.2185 | 0.0696 |
86
+ | 0.0263 | 68.3 | 32000 | 0.0215 | 0.2167 | 0.0696 |
87
+ | 0.0299 | 70.43 | 33000 | 0.0217 | 0.2201 | 0.0709 |
88
+ | 0.0273 | 72.56 | 34000 | 0.0222 | 0.2164 | 0.0724 |
89
+ | 0.0269 | 74.7 | 35000 | 0.0220 | 0.2240 | 0.0693 |
90
+ | 0.0264 | 76.92 | 36000 | 0.2220 | 0.0218 | 0.0704 |
91
+ | 0.0257 | 79.05 | 37000 | 0.2229 | 0.0217 | 0.0688 |
92
+ | 0.0251 | 81.19 | 38000 | 0.2263 | 0.0215 | 0.0694 |
93
+ | 0.0245 | 83.32 | 39000 | 0.2253 | 0.0210 | 0.0673 |
94
+ | 0.0243 | 85.45 | 40000 | 0.2264 | 0.0215 | 0.0692 |
95
+ | 0.0236 | 87.59 | 41000 | 0.2261 | 0.0217 | 0.0689 |
96
+ | 0.0225 | 89.72 | 42000 | 0.2265 | 0.0212 | 0.0680 |
97
+ | 0.023 | 91.85 | 43000 | 0.2265 | 0.0210 | 0.0674 |
98
+ | 0.0217 | 93.99 | 44000 | 0.2265 | 0.0209 | 0.0677 |
99
+ | 0.022 | 96.12 | 45000 | 0.2254 | 0.0211 | 0.0685 |
100
+ | 0.0219 | 98.25 | 46000 | 0.2262 | 0.0208 | 0.0672 |
101
+
102
+
103
+ ### Framework versions
104
+
105
+ - Transformers 4.29.1
106
+ - Pytorch 2.0.1+cu118
107
+ - Datasets 2.12.0
108
+ - Tokenizers 0.13.3