|
--- |
|
license: apache-2.0 |
|
base_model: facebook/wav2vec2-large-xlsr-53 |
|
tags: |
|
- automatic-speech-recognition |
|
- DewiBrynJones/banc-trawsgrifiadau-bangor-clean-with-ccv |
|
- generated_from_trainer |
|
metrics: |
|
- wer |
|
model-index: |
|
- name: wav2vec2-xlsr-53-ft-btb-ccv-cy |
|
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-xlsr-53-ft-btb-ccv-cy |
|
|
|
This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the DEWIBRYNJONES/BANC-TRAWSGRIFIADAU-BANGOR-CLEAN-WITH-CCV - DEFAULT dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: inf |
|
- Wer: 0.3289 |
|
|
|
## 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: 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 |
|
- training_steps: 6000 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Wer | |
|
|:-------------:|:------:|:----:|:---------------:|:------:| |
|
| No log | 0.0772 | 200 | inf | 1.0 | |
|
| No log | 0.1544 | 400 | inf | 0.9938 | |
|
| 3.9317 | 0.2317 | 600 | inf | 0.7576 | |
|
| 3.9317 | 0.3089 | 800 | inf | 0.6942 | |
|
| 0.9699 | 0.3861 | 1000 | inf | 0.5763 | |
|
| 0.9699 | 0.4633 | 1200 | inf | 0.5519 | |
|
| 0.9699 | 0.5405 | 1400 | inf | 0.5174 | |
|
| 0.8031 | 0.6178 | 1600 | inf | 0.5338 | |
|
| 0.8031 | 0.6950 | 1800 | inf | 0.4777 | |
|
| 0.7169 | 0.7722 | 2000 | inf | 0.4504 | |
|
| 0.7169 | 0.8494 | 2200 | inf | 0.4500 | |
|
| 0.7169 | 0.9266 | 2400 | inf | 0.4432 | |
|
| 0.6687 | 1.0039 | 2600 | inf | 0.4176 | |
|
| 0.6687 | 1.0811 | 2800 | inf | 0.4054 | |
|
| 0.5609 | 1.1583 | 3000 | inf | 0.4009 | |
|
| 0.5609 | 1.2355 | 3200 | inf | 0.4023 | |
|
| 0.5609 | 1.3127 | 3400 | inf | 0.3919 | |
|
| 0.5324 | 1.3900 | 3600 | inf | 0.3795 | |
|
| 0.5324 | 1.4672 | 3800 | inf | 0.3752 | |
|
| 0.5196 | 1.5444 | 4000 | inf | 0.3662 | |
|
| 0.5196 | 1.6216 | 4200 | inf | 0.3703 | |
|
| 0.5196 | 1.6988 | 4400 | inf | 0.3614 | |
|
| 0.4967 | 1.7761 | 4600 | inf | 0.3530 | |
|
| 0.4967 | 1.8533 | 4800 | inf | 0.3481 | |
|
| 0.4735 | 1.9305 | 5000 | inf | 0.3506 | |
|
| 0.4735 | 2.0077 | 5200 | inf | 0.3432 | |
|
| 0.4735 | 2.0849 | 5400 | inf | 0.3369 | |
|
| 0.4244 | 2.1622 | 5600 | inf | 0.3296 | |
|
| 0.4244 | 2.2394 | 5800 | inf | 0.3295 | |
|
| 0.3674 | 2.3166 | 6000 | inf | 0.3289 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.41.2 |
|
- Pytorch 2.3.1+cu121 |
|
- Datasets 2.20.0 |
|
- Tokenizers 0.19.1 |
|
|
