|
--- |
|
language: |
|
- ur |
|
license: apache-2.0 |
|
tags: |
|
- automatic-speech-recognition |
|
- mozilla-foundation/common_voice_8_0 |
|
- generated_from_trainer |
|
datasets: |
|
- common_voice |
|
model-index: |
|
- name: '' |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# |
|
|
|
This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the MOZILLA-FOUNDATION/COMMON_VOICE_8_0 - UR dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.9580 |
|
- Wer: 0.6520 |
|
|
|
## Model description |
|
|
|
More information needed |
|
|
|
## Intended uses & limitations |
|
|
|
More information needed |
|
|
|
## Training and evaluation data |
|
|
|
More information needed |
|
|
|
## Training procedure |
|
|
|
### Training hyperparameters |
|
|
|
The following hyperparameters were used during training: |
|
- learning_rate: 7.5e-05 |
|
- train_batch_size: 8 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 2 |
|
- total_train_batch_size: 16 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 50 |
|
- num_epochs: 50.0 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Wer | |
|
|:-------------:|:-----:|:----:|:---------------:|:------:| |
|
| 9.5036 | 1.96 | 100 | 4.0538 | 1.0 | |
|
| 3.3669 | 3.92 | 200 | 3.2041 | 1.0 | |
|
| 3.1499 | 5.88 | 300 | 3.1220 | 1.0 | |
|
| 3.0271 | 7.84 | 400 | 2.9935 | 0.9970 | |
|
| 2.9565 | 9.8 | 500 | 2.9357 | 0.9993 | |
|
| 2.9184 | 11.76 | 600 | 2.9165 | 0.9963 | |
|
| 2.8832 | 13.73 | 700 | 2.8762 | 0.9911 | |
|
| 2.8407 | 15.69 | 800 | 2.8102 | 0.9970 | |
|
| 2.7007 | 17.65 | 900 | 2.4364 | 0.9963 | |
|
| 2.4206 | 19.61 | 1000 | 1.9852 | 0.9421 | |
|
| 2.0699 | 21.57 | 1100 | 1.4849 | 0.8343 | |
|
| 1.8311 | 23.53 | 1200 | 1.3084 | 0.7801 | |
|
| 1.7127 | 25.49 | 1300 | 1.2040 | 0.7446 | |
|
| 1.6239 | 27.45 | 1400 | 1.1359 | 0.7280 | |
|
| 1.5654 | 29.41 | 1500 | 1.0688 | 0.7159 | |
|
| 1.4965 | 31.37 | 1600 | 1.0520 | 0.6985 | |
|
| 1.445 | 33.33 | 1700 | 1.0314 | 0.6878 | |
|
| 1.4095 | 35.29 | 1800 | 1.0063 | 0.6712 | |
|
| 1.3853 | 37.25 | 1900 | 0.9848 | 0.6701 | |
|
| 1.3558 | 39.22 | 2000 | 0.9738 | 0.6731 | |
|
| 1.3415 | 41.18 | 2100 | 0.9656 | 0.6646 | |
|
| 1.3102 | 43.14 | 2200 | 0.9632 | 0.6557 | |
|
| 1.309 | 45.1 | 2300 | 0.9496 | 0.6557 | |
|
| 1.2993 | 47.06 | 2400 | 0.9609 | 0.6550 | |
|
| 1.2695 | 49.02 | 2500 | 0.9604 | 0.6542 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.17.0.dev0 |
|
- Pytorch 1.10.2+cu102 |
|
- Datasets 1.18.3 |
|
- Tokenizers 0.11.0 |
|
|
