update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,113 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
datasets:
|
| 6 |
+
- common_voice_8_0
|
| 7 |
+
metrics:
|
| 8 |
+
- wer
|
| 9 |
+
model-index:
|
| 10 |
+
- name: wav2vec2-large-xls-r-1b-frisian-cv-8-10m
|
| 11 |
+
results:
|
| 12 |
+
- task:
|
| 13 |
+
name: Automatic Speech Recognition
|
| 14 |
+
type: automatic-speech-recognition
|
| 15 |
+
dataset:
|
| 16 |
+
name: common_voice_8_0
|
| 17 |
+
type: common_voice_8_0
|
| 18 |
+
config: fy-NL
|
| 19 |
+
split: validation
|
| 20 |
+
args: fy-NL
|
| 21 |
+
metrics:
|
| 22 |
+
- name: Wer
|
| 23 |
+
type: wer
|
| 24 |
+
value: 0.09612912441079846
|
| 25 |
+
---
|
| 26 |
+
|
| 27 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 28 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 29 |
+
|
| 30 |
+
# wav2vec2-large-xls-r-1b-frisian-cv-8-10m
|
| 31 |
+
|
| 32 |
+
This model is a fine-tuned version of [facebook/wav2vec2-xls-r-1b](https://huggingface.co/facebook/wav2vec2-xls-r-1b) on the common_voice_8_0 dataset.
|
| 33 |
+
It achieves the following results on the evaluation set:
|
| 34 |
+
- Loss: 0.1207
|
| 35 |
+
- Wer: 0.0961
|
| 36 |
+
|
| 37 |
+
## Model description
|
| 38 |
+
|
| 39 |
+
More information needed
|
| 40 |
+
|
| 41 |
+
## Intended uses & limitations
|
| 42 |
+
|
| 43 |
+
More information needed
|
| 44 |
+
|
| 45 |
+
## Training and evaluation data
|
| 46 |
+
|
| 47 |
+
More information needed
|
| 48 |
+
|
| 49 |
+
## Training procedure
|
| 50 |
+
|
| 51 |
+
### Training hyperparameters
|
| 52 |
+
|
| 53 |
+
The following hyperparameters were used during training:
|
| 54 |
+
- learning_rate: 5e-05
|
| 55 |
+
- train_batch_size: 32
|
| 56 |
+
- eval_batch_size: 8
|
| 57 |
+
- seed: 42
|
| 58 |
+
- optimizer: Adam with betas=(0.9,0.98) and epsilon=1e-08
|
| 59 |
+
- lr_scheduler_type: linear
|
| 60 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 61 |
+
- num_epochs: 50
|
| 62 |
+
- mixed_precision_training: Native AMP
|
| 63 |
+
|
| 64 |
+
### Training results
|
| 65 |
+
|
| 66 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 67 |
+
|:-------------:|:-----:|:-----:|:---------------:|:------:|
|
| 68 |
+
| 5.6342 | 1.32 | 300 | 2.9760 | 1.0 |
|
| 69 |
+
| 2.2716 | 2.63 | 600 | 0.6877 | 0.6024 |
|
| 70 |
+
| 1.1303 | 3.95 | 900 | 0.3522 | 0.3450 |
|
| 71 |
+
| 0.9038 | 5.26 | 1200 | 0.2714 | 0.2603 |
|
| 72 |
+
| 0.846 | 6.58 | 1500 | 0.2143 | 0.2036 |
|
| 73 |
+
| 0.8044 | 7.89 | 1800 | 0.1829 | 0.1788 |
|
| 74 |
+
| 0.7069 | 9.21 | 2100 | 0.1751 | 0.1667 |
|
| 75 |
+
| 0.6995 | 10.53 | 2400 | 0.1741 | 0.1727 |
|
| 76 |
+
| 0.7115 | 11.84 | 2700 | 0.1591 | 0.1486 |
|
| 77 |
+
| 0.677 | 13.16 | 3000 | 0.1636 | 0.1459 |
|
| 78 |
+
| 0.6032 | 14.47 | 3300 | 0.1535 | 0.1439 |
|
| 79 |
+
| 0.6218 | 15.79 | 3600 | 0.1427 | 0.1406 |
|
| 80 |
+
| 0.6519 | 17.11 | 3900 | 0.1498 | 0.1488 |
|
| 81 |
+
| 0.5739 | 18.42 | 4200 | 0.1438 | 0.1319 |
|
| 82 |
+
| 0.567 | 19.74 | 4500 | 0.1379 | 0.1322 |
|
| 83 |
+
| 0.4982 | 21.05 | 4800 | 0.1315 | 0.1237 |
|
| 84 |
+
| 0.5825 | 22.37 | 5100 | 0.1349 | 0.1252 |
|
| 85 |
+
| 0.5085 | 23.68 | 5400 | 0.1297 | 0.1233 |
|
| 86 |
+
| 0.4946 | 25.0 | 5700 | 0.1343 | 0.1127 |
|
| 87 |
+
| 0.5677 | 26.32 | 6000 | 0.1323 | 0.1228 |
|
| 88 |
+
| 0.4858 | 27.63 | 6300 | 0.1292 | 0.1098 |
|
| 89 |
+
| 0.4709 | 28.95 | 6600 | 0.1267 | 0.1204 |
|
| 90 |
+
| 0.3241 | 30.26 | 6900 | 0.1315 | 0.1274 |
|
| 91 |
+
| 0.2796 | 31.58 | 7200 | 0.1315 | 0.1202 |
|
| 92 |
+
| 0.3171 | 32.89 | 7500 | 0.1315 | 0.1200 |
|
| 93 |
+
| 0.2591 | 34.21 | 7800 | 0.1322 | 0.1106 |
|
| 94 |
+
| 0.2716 | 35.53 | 8100 | 0.1233 | 0.1030 |
|
| 95 |
+
| 0.2446 | 36.84 | 8400 | 0.1273 | 0.1087 |
|
| 96 |
+
| 0.2377 | 38.16 | 8700 | 0.1243 | 0.1101 |
|
| 97 |
+
| 0.2183 | 39.47 | 9000 | 0.1230 | 0.1116 |
|
| 98 |
+
| 0.2059 | 40.79 | 9300 | 0.1240 | 0.1001 |
|
| 99 |
+
| 0.1916 | 42.11 | 9600 | 0.1223 | 0.1003 |
|
| 100 |
+
| 0.196 | 43.42 | 9900 | 0.1246 | 0.0965 |
|
| 101 |
+
| 0.1969 | 44.74 | 10200 | 0.1222 | 0.1038 |
|
| 102 |
+
| 0.1951 | 46.05 | 10500 | 0.1208 | 0.1003 |
|
| 103 |
+
| 0.1809 | 47.37 | 10800 | 0.1213 | 0.1003 |
|
| 104 |
+
| 0.1793 | 48.68 | 11100 | 0.1202 | 0.0959 |
|
| 105 |
+
| 0.1837 | 50.0 | 11400 | 0.1207 | 0.0961 |
|
| 106 |
+
|
| 107 |
+
|
| 108 |
+
### Framework versions
|
| 109 |
+
|
| 110 |
+
- Transformers 4.28.1
|
| 111 |
+
- Pytorch 2.0.0+cu117
|
| 112 |
+
- Datasets 2.11.0
|
| 113 |
+
- Tokenizers 0.13.3
|