metadata
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: []
wav2vec2-xlsr-53-ft-btb-ccv-cy
This model is a fine-tuned version of 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: 0.3665
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: 64
- 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: 2000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| No log | 0.3086 | 200 | inf | 1.0 |
| No log | 0.6173 | 400 | inf | 0.9468 |
| 3.8579 | 0.9259 | 600 | inf | 0.6823 |
| 3.8579 | 1.2346 | 800 | inf | 0.5246 |
| 0.7662 | 1.5432 | 1000 | inf | 0.4560 |
| 0.7662 | 1.8519 | 1200 | inf | 0.4314 |
| 0.7662 | 2.1605 | 1400 | inf | 0.4371 |
| 0.5916 | 2.4691 | 1600 | inf | 0.3861 |
| 0.5916 | 2.7778 | 1800 | inf | 0.3649 |
| 0.4977 | 3.0864 | 2000 | inf | 0.3665 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1