Commit
·
ae132fe
1
Parent(s):
2c6842d
update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,86 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
datasets:
|
| 6 |
+
- common_voice
|
| 7 |
+
model-index:
|
| 8 |
+
- name: wav2vec2-large-xls-r-300m-gn-k1
|
| 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 |
+
# wav2vec2-large-xls-r-300m-gn-k1
|
| 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: 0.9220
|
| 20 |
+
- Wer: 0.6631
|
| 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: 0.00018
|
| 40 |
+
- train_batch_size: 16
|
| 41 |
+
- eval_batch_size: 8
|
| 42 |
+
- seed: 42
|
| 43 |
+
- gradient_accumulation_steps: 2
|
| 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: 600
|
| 48 |
+
- num_epochs: 200
|
| 49 |
+
- mixed_precision_training: Native AMP
|
| 50 |
+
|
| 51 |
+
### Training results
|
| 52 |
+
|
| 53 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 54 |
+
|:-------------:|:------:|:----:|:---------------:|:------:|
|
| 55 |
+
| 15.9402 | 8.32 | 100 | 6.9185 | 1.0 |
|
| 56 |
+
| 4.6367 | 16.64 | 200 | 3.7416 | 1.0 |
|
| 57 |
+
| 3.4337 | 24.96 | 300 | 3.2581 | 1.0 |
|
| 58 |
+
| 3.2307 | 33.32 | 400 | 2.8008 | 1.0 |
|
| 59 |
+
| 1.3182 | 41.64 | 500 | 0.8359 | 0.8171 |
|
| 60 |
+
| 0.409 | 49.96 | 600 | 0.8470 | 0.8323 |
|
| 61 |
+
| 0.2573 | 58.32 | 700 | 0.7823 | 0.7576 |
|
| 62 |
+
| 0.1969 | 66.64 | 800 | 0.8306 | 0.7424 |
|
| 63 |
+
| 0.1469 | 74.96 | 900 | 0.9225 | 0.7713 |
|
| 64 |
+
| 0.1172 | 83.32 | 1000 | 0.7903 | 0.6951 |
|
| 65 |
+
| 0.1017 | 91.64 | 1100 | 0.8519 | 0.6921 |
|
| 66 |
+
| 0.0851 | 99.96 | 1200 | 0.8129 | 0.6646 |
|
| 67 |
+
| 0.071 | 108.32 | 1300 | 0.8614 | 0.7043 |
|
| 68 |
+
| 0.061 | 116.64 | 1400 | 0.8414 | 0.6921 |
|
| 69 |
+
| 0.0552 | 124.96 | 1500 | 0.8649 | 0.6905 |
|
| 70 |
+
| 0.0465 | 133.32 | 1600 | 0.8575 | 0.6646 |
|
| 71 |
+
| 0.0381 | 141.64 | 1700 | 0.8802 | 0.6723 |
|
| 72 |
+
| 0.0338 | 149.96 | 1800 | 0.8731 | 0.6845 |
|
| 73 |
+
| 0.0306 | 158.32 | 1900 | 0.9003 | 0.6585 |
|
| 74 |
+
| 0.0236 | 166.64 | 2000 | 0.9408 | 0.6616 |
|
| 75 |
+
| 0.021 | 174.96 | 2100 | 0.9353 | 0.6723 |
|
| 76 |
+
| 0.0212 | 183.32 | 2200 | 0.9269 | 0.6570 |
|
| 77 |
+
| 0.0191 | 191.64 | 2300 | 0.9277 | 0.6662 |
|
| 78 |
+
| 0.0161 | 199.96 | 2400 | 0.9220 | 0.6631 |
|
| 79 |
+
|
| 80 |
+
|
| 81 |
+
### Framework versions
|
| 82 |
+
|
| 83 |
+
- Transformers 4.16.2
|
| 84 |
+
- Pytorch 1.10.0+cu111
|
| 85 |
+
- Datasets 1.18.3
|
| 86 |
+
- Tokenizers 0.11.0
|