|
|
--- |
|
|
library_name: transformers |
|
|
license: apache-2.0 |
|
|
base_model: facebook/wav2vec2-xls-r-1b |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
model-index: |
|
|
- name: wav2vec2-1b-E10_freq_pause_speed |
|
|
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. --> |
|
|
|
|
|
# wav2vec2-1b-E10_freq_pause_speed |
|
|
|
|
|
This model is a fine-tuned version of [facebook/wav2vec2-xls-r-1b](https://huggingface.co/facebook/wav2vec2-xls-r-1b) on an unknown dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 1.0591 |
|
|
- Cer: 29.8990 |
|
|
|
|
|
## 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: 2 |
|
|
- eval_batch_size: 8 |
|
|
- seed: 42 |
|
|
- gradient_accumulation_steps: 8 |
|
|
- 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: 5 |
|
|
- mixed_precision_training: Native AMP |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Cer | |
|
|
|:-------------:|:------:|:----:|:---------------:|:-------:| |
|
|
| 14.1255 | 0.2580 | 200 | 4.9067 | 98.6372 | |
|
|
| 4.7267 | 0.5160 | 400 | 4.8958 | 92.8806 | |
|
|
| 4.5507 | 0.7741 | 600 | 4.7162 | 92.6281 | |
|
|
| 4.3966 | 1.0321 | 800 | 4.4020 | 92.5928 | |
|
|
| 3.6541 | 1.2901 | 1000 | 2.9100 | 59.9918 | |
|
|
| 1.9909 | 1.5481 | 1200 | 2.1571 | 52.5200 | |
|
|
| 1.4189 | 1.8062 | 1400 | 1.6267 | 39.1506 | |
|
|
| 1.1011 | 2.0642 | 1600 | 1.6680 | 44.1259 | |
|
|
| 0.8993 | 2.3222 | 1800 | 1.6389 | 43.5562 | |
|
|
| 0.8212 | 2.5802 | 2000 | 1.6651 | 42.0054 | |
|
|
| 0.7402 | 2.8383 | 2200 | 1.3370 | 37.4413 | |
|
|
| 0.671 | 3.0963 | 2400 | 1.2070 | 34.4690 | |
|
|
| 0.551 | 3.3543 | 2600 | 1.2536 | 35.7554 | |
|
|
| 0.4977 | 3.6123 | 2800 | 1.1724 | 33.1062 | |
|
|
| 0.4612 | 3.8703 | 3000 | 1.0322 | 29.5700 | |
|
|
| 0.4048 | 4.1284 | 3200 | 1.0640 | 30.6156 | |
|
|
| 0.3543 | 4.3864 | 3400 | 1.1424 | 30.9974 | |
|
|
| 0.3354 | 4.6444 | 3600 | 1.0794 | 29.9577 | |
|
|
| 0.3099 | 4.9024 | 3800 | 1.0591 | 29.8990 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.45.2 |
|
|
- Pytorch 2.3.1.post100 |
|
|
- Datasets 2.19.1 |
|
|
- Tokenizers 0.20.1 |
|
|
|
