|
--- |
|
license: apache-2.0 |
|
tags: |
|
- generated_from_trainer |
|
base_model: facebook/wav2vec2-xls-r-300m |
|
model-index: |
|
- name: wav2vec2-xls-r-300m-phoneme |
|
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. --> |
|
|
|
# wav2vec2-xls-r-300m-phoneme |
|
|
|
This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.3327 |
|
- Cer: 0.1332 |
|
|
|
## 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: 3e-05 |
|
- train_batch_size: 8 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 4 |
|
- total_train_batch_size: 32 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 2000 |
|
- training_steps: 7000 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Cer | |
|
|:-------------:|:-----:|:----:|:---------------:|:------:| |
|
| 3.4324 | 1.32 | 1000 | 3.3693 | 0.9091 | |
|
| 2.1751 | 2.65 | 2000 | 1.1382 | 0.2397 | |
|
| 1.3986 | 3.97 | 3000 | 0.4886 | 0.1452 | |
|
| 1.2285 | 5.3 | 4000 | 0.3842 | 0.1351 | |
|
| 1.142 | 6.62 | 5000 | 0.3505 | 0.1349 | |
|
| 1.1075 | 7.95 | 6000 | 0.3323 | 0.1317 | |
|
| 1.0867 | 9.27 | 7000 | 0.3265 | 0.1315 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.17.0.dev0 |
|
- Pytorch 1.10.2+cu102 |
|
- Datasets 1.18.2.dev0 |
|
- Tokenizers 0.11.0 |
|
|
