update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,94 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language:
|
| 3 |
+
- ja
|
| 4 |
+
license: apache-2.0
|
| 5 |
+
tags:
|
| 6 |
+
- automatic-speech-recognition
|
| 7 |
+
- vumichien/common_voice_large_jsut_jsss_css10
|
| 8 |
+
- generated_from_trainer
|
| 9 |
+
model-index:
|
| 10 |
+
- name: wav2vec2-xls-r-1b-ja-dumy8
|
| 11 |
+
results: []
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
+
|
| 17 |
+
# wav2vec2-xls-r-1b-ja-dumy8
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [facebook/wav2vec2-xls-r-1b](https://huggingface.co/facebook/wav2vec2-xls-r-1b) on the VUMICHIEN/COMMON_VOICE_LARGE_JSUT_JSSS_CSS10 - JA dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.2104
|
| 22 |
+
- Wer: 0.1941
|
| 23 |
+
- Cer: 0.0991
|
| 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: 5e-05
|
| 43 |
+
- train_batch_size: 16
|
| 44 |
+
- eval_batch_size: 8
|
| 45 |
+
- seed: 42
|
| 46 |
+
- gradient_accumulation_steps: 4
|
| 47 |
+
- total_train_batch_size: 64
|
| 48 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 49 |
+
- lr_scheduler_type: linear
|
| 50 |
+
- lr_scheduler_warmup_steps: 1000
|
| 51 |
+
- num_epochs: 100.0
|
| 52 |
+
- mixed_precision_training: Native AMP
|
| 53 |
+
|
| 54 |
+
### Training results
|
| 55 |
+
|
| 56 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
|
| 57 |
+
|:-------------:|:-----:|:-----:|:---------------:|:------:|:------:|
|
| 58 |
+
| 2.2896 | 3.37 | 1500 | 0.4748 | 0.4013 | 0.1767 |
|
| 59 |
+
| 1.1608 | 6.74 | 3000 | 0.3350 | 0.3159 | 0.1456 |
|
| 60 |
+
| 1.1042 | 10.11 | 4500 | 0.3119 | 0.2971 | 0.1400 |
|
| 61 |
+
| 1.0494 | 13.48 | 6000 | 0.2974 | 0.2867 | 0.1353 |
|
| 62 |
+
| 1.0061 | 16.85 | 7500 | 0.2802 | 0.2746 | 0.1300 |
|
| 63 |
+
| 0.9629 | 20.22 | 9000 | 0.2844 | 0.2776 | 0.1326 |
|
| 64 |
+
| 0.9267 | 23.59 | 10500 | 0.2577 | 0.2603 | 0.1255 |
|
| 65 |
+
| 0.8984 | 26.96 | 12000 | 0.2508 | 0.2531 | 0.1226 |
|
| 66 |
+
| 0.8729 | 30.34 | 13500 | 0.2629 | 0.2606 | 0.1254 |
|
| 67 |
+
| 0.8546 | 33.71 | 15000 | 0.2402 | 0.2447 | 0.1193 |
|
| 68 |
+
| 0.8304 | 37.08 | 16500 | 0.2532 | 0.2472 | 0.1209 |
|
| 69 |
+
| 0.8075 | 40.45 | 18000 | 0.2439 | 0.2469 | 0.1198 |
|
| 70 |
+
| 0.7827 | 43.82 | 19500 | 0.2387 | 0.2372 | 0.1167 |
|
| 71 |
+
| 0.7627 | 47.19 | 21000 | 0.2344 | 0.2331 | 0.1147 |
|
| 72 |
+
| 0.7402 | 50.56 | 22500 | 0.2314 | 0.2299 | 0.1135 |
|
| 73 |
+
| 0.718 | 53.93 | 24000 | 0.2257 | 0.2267 | 0.1114 |
|
| 74 |
+
| 0.7016 | 57.3 | 25500 | 0.2204 | 0.2184 | 0.1089 |
|
| 75 |
+
| 0.6804 | 60.67 | 27000 | 0.2227 | 0.2181 | 0.1085 |
|
| 76 |
+
| 0.6625 | 64.04 | 28500 | 0.2138 | 0.2112 | 0.1058 |
|
| 77 |
+
| 0.6465 | 67.42 | 30000 | 0.2141 | 0.2081 | 0.1044 |
|
| 78 |
+
| 0.6238 | 70.79 | 31500 | 0.2172 | 0.2082 | 0.1050 |
|
| 79 |
+
| 0.6062 | 74.16 | 33000 | 0.2174 | 0.2058 | 0.1043 |
|
| 80 |
+
| 0.588 | 77.53 | 34500 | 0.2156 | 0.2034 | 0.1027 |
|
| 81 |
+
| 0.5722 | 80.9 | 36000 | 0.2162 | 0.2032 | 0.1029 |
|
| 82 |
+
| 0.5585 | 84.27 | 37500 | 0.2156 | 0.2022 | 0.1021 |
|
| 83 |
+
| 0.5456 | 87.64 | 39000 | 0.2126 | 0.1993 | 0.1009 |
|
| 84 |
+
| 0.5325 | 91.01 | 40500 | 0.2121 | 0.1966 | 0.1003 |
|
| 85 |
+
| 0.5229 | 94.38 | 42000 | 0.2104 | 0.1941 | 0.0991 |
|
| 86 |
+
| 0.5134 | 97.75 | 43500 | 0.2108 | 0.1948 | 0.0992 |
|
| 87 |
+
|
| 88 |
+
|
| 89 |
+
### Framework versions
|
| 90 |
+
|
| 91 |
+
- Transformers 4.16.0.dev0
|
| 92 |
+
- Pytorch 1.10.1+cu102
|
| 93 |
+
- Datasets 1.17.1.dev0
|
| 94 |
+
- Tokenizers 0.11.0
|