|
--- |
|
license: apache-2.0 |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: 20220517-045629 |
|
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. --> |
|
|
|
# 20220517-045629 |
|
|
|
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: 0.3700 |
|
- Wer: 0.4581 |
|
- Cer: 0.0854 |
|
|
|
## 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: 0.0001 |
|
- train_batch_size: 8 |
|
- eval_batch_size: 8 |
|
- seed: 1339 |
|
- gradient_accumulation_steps: 8 |
|
- total_train_batch_size: 64 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 100 |
|
- num_epochs: 2 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer | |
|
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:| |
|
| 5.238 | 0.29 | 200 | 3.1770 | 1.0 | 1.0 | |
|
| 2.165 | 0.59 | 400 | 0.7309 | 0.7144 | 0.1543 | |
|
| 0.7022 | 0.88 | 600 | 0.4614 | 0.5521 | 0.1058 | |
|
| 0.5114 | 1.17 | 800 | 0.4202 | 0.4998 | 0.0965 | |
|
| 0.4482 | 1.47 | 1000 | 0.3786 | 0.4645 | 0.0877 | |
|
| 0.4082 | 1.76 | 1200 | 0.3700 | 0.4581 | 0.0854 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.18.0.dev0 |
|
- Pytorch 1.10.0+cu113 |
|
- Datasets 2.1.0 |
|
- Tokenizers 0.11.6 |
|
|
