|
--- |
|
license: apache-2.0 |
|
base_model: facebook/wav2vec2-large |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- wer |
|
model-index: |
|
- name: wav2vec2_large_1.1 |
|
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_large_1.1 |
|
|
|
This model is a fine-tuned version of [facebook/wav2vec2-large](https://huggingface.co/facebook/wav2vec2-large) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 3.1063 |
|
- Wer: 1.0 |
|
- Cer: 0.9997 |
|
|
|
## 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: 0.001 |
|
- train_batch_size: 16 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 500 |
|
- num_epochs: 5 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer | |
|
|:-------------:|:-----:|:----:|:---------------:|:---:|:------:| |
|
| 3.8007 | 1.12 | 700 | 3.0604 | 1.0 | 0.9997 | |
|
| 3.3783 | 2.24 | 1400 | 3.2217 | 1.0 | 0.9997 | |
|
| 3.2938 | 3.36 | 2100 | 3.1471 | 1.0 | 0.9997 | |
|
| 3.2049 | 4.48 | 2800 | 3.1063 | 1.0 | 0.9997 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.39.3 |
|
- Pytorch 2.1.2 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |
|
|
