metadata
library_name: transformers
license: cc-by-nc-4.0
base_model: facebook/mms-300m
tags:
- automatic-speech-recognition
- libri10h
- mms
- generated_from_trainer
metrics:
- wer
model-index:
- name: wav2vec2-300m-librispeech-test
results: []
wav2vec2-300m-librispeech-test
This model is a fine-tuned version of facebook/mms-300m on the LIBRI10H - ENG dataset. It achieves the following results on the evaluation set:
- Loss: 2.8825
- Wer: 1.0
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: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 8
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- num_epochs: 2.0
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 6.037 | 0.2899 | 100 | 2.9196 | 1.0 |
| 2.8559 | 0.5797 | 200 | 2.8880 | 1.0 |
| 2.8547 | 0.8696 | 300 | 2.8900 | 1.0 |
| 2.8418 | 1.1594 | 400 | 2.9082 | 1.0 |
| 2.8436 | 1.4493 | 500 | 2.8775 | 1.0 |
| 2.8373 | 1.7391 | 600 | 2.8821 | 1.0 |
Framework versions
- Transformers 4.49.0
- Pytorch 2.6.0+cu124
- Datasets 3.3.2
- Tokenizers 0.21.0