update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,79 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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-lv-v05
|
| 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-lv-v05
|
| 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: 0.3862
|
| 20 |
+
- Wer: 0.2588
|
| 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: 0.0003
|
| 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: 500
|
| 48 |
+
- num_epochs: 50
|
| 49 |
+
- mixed_precision_training: Native AMP
|
| 50 |
+
|
| 51 |
+
### Training results
|
| 52 |
+
|
| 53 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 54 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
| 55 |
+
| 4.8836 | 2.81 | 400 | 0.8722 | 0.7244 |
|
| 56 |
+
| 0.5365 | 5.63 | 800 | 0.4622 | 0.4812 |
|
| 57 |
+
| 0.277 | 8.45 | 1200 | 0.4348 | 0.4056 |
|
| 58 |
+
| 0.1947 | 11.27 | 1600 | 0.4223 | 0.3636 |
|
| 59 |
+
| 0.1655 | 14.08 | 2000 | 0.4084 | 0.3465 |
|
| 60 |
+
| 0.1441 | 16.9 | 2400 | 0.4329 | 0.3497 |
|
| 61 |
+
| 0.121 | 19.72 | 2800 | 0.4371 | 0.3324 |
|
| 62 |
+
| 0.1062 | 22.53 | 3200 | 0.4202 | 0.3198 |
|
| 63 |
+
| 0.0937 | 25.35 | 3600 | 0.4063 | 0.3265 |
|
| 64 |
+
| 0.0871 | 28.17 | 4000 | 0.4253 | 0.3255 |
|
| 65 |
+
| 0.0755 | 30.98 | 4400 | 0.4368 | 0.3194 |
|
| 66 |
+
| 0.0627 | 33.8 | 4800 | 0.4067 | 0.2908 |
|
| 67 |
+
| 0.0595 | 36.62 | 5200 | 0.3929 | 0.2973 |
|
| 68 |
+
| 0.0523 | 39.44 | 5600 | 0.3748 | 0.2817 |
|
| 69 |
+
| 0.0434 | 42.25 | 6000 | 0.3769 | 0.2711 |
|
| 70 |
+
| 0.0391 | 45.07 | 6400 | 0.3901 | 0.2653 |
|
| 71 |
+
| 0.0319 | 47.88 | 6800 | 0.3862 | 0.2588 |
|
| 72 |
+
|
| 73 |
+
|
| 74 |
+
### Framework versions
|
| 75 |
+
|
| 76 |
+
- Transformers 4.11.3
|
| 77 |
+
- Pytorch 1.10.0+cu111
|
| 78 |
+
- Datasets 1.13.3
|
| 79 |
+
- Tokenizers 0.10.3
|