|
--- |
|
license: apache-2.0 |
|
base_model: facebook/wav2vec2-large-xlsr-53 |
|
tags: |
|
- automatic-speech-recognition |
|
- ./sample_speech.py |
|
- generated_from_trainer |
|
model-index: |
|
- name: zhko_xlsr_run1 |
|
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. --> |
|
|
|
# zhko_xlsr_run1 |
|
|
|
This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the ./SAMPLE_SPEECH.PY - NA dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 2.1948 |
|
- Cer: 0.4465 |
|
|
|
## 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: 0.0003 |
|
- train_batch_size: 2 |
|
- eval_batch_size: 2 |
|
- seed: 42 |
|
- distributed_type: multi-GPU |
|
- gradient_accumulation_steps: 2 |
|
- total_train_batch_size: 4 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 500 |
|
- num_epochs: 10 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Cer | |
|
|:-------------:|:-----:|:-----:|:---------------:|:------:| |
|
| 5.0444 | 1.0 | 6593 | 4.6695 | 0.8764 | |
|
| 3.2619 | 2.0 | 13186 | 2.9759 | 0.6249 | |
|
| 2.7859 | 3.0 | 19779 | 2.5370 | 0.5421 | |
|
| 2.3947 | 4.0 | 26372 | 2.3582 | 0.5159 | |
|
| 2.1313 | 5.0 | 32965 | 2.2462 | 0.4872 | |
|
| 1.8083 | 6.0 | 39558 | 2.2104 | 0.4696 | |
|
| 1.5209 | 7.0 | 46151 | 2.1621 | 0.4661 | |
|
| 1.3735 | 8.0 | 52744 | 2.2031 | 0.4582 | |
|
| 1.1354 | 9.0 | 59337 | 2.1740 | 0.4492 | |
|
| 1.0788 | 10.0 | 65930 | 2.1948 | 0.4465 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.34.1 |
|
- Pytorch 2.1.0+cu121 |
|
- Datasets 2.14.6 |
|
- Tokenizers 0.14.1 |
|
|
