---
library_name: transformers
license: cc-by-nc-4.0
base_model: facebook/mms-1b-all
tags:
- generated_from_trainer
datasets:
- common_voice_17_0
metrics:
- wer
- bleu
model-index:
- name: wav2vec2-mms-1b-CV17.0
  results:
  - task:
      name: Automatic Speech Recognition
      type: automatic-speech-recognition
    dataset:
      name: common_voice_17_0
      type: common_voice_17_0
    metrics:
    - name: Wer
      type: wer
      value: 0.6538388264431321
    - name: Bleu
      type: bleu
      value: 0.14202013774436864
---


# wav2vec2-mms-1b-CV17.0

This model is a fine-tuned version of [facebook/mms-1b-all](https://huggingface.co/facebook/mms-1b-all) on the common_voice_17_0 dataset.
Adapters for several languages were trained.

## Intended uses & limitations

Speech-to-text transciption of Malayalam, Tamil, Telugu, and Yoruba.

### Training hyperparameters

The following hyperparameters were used during training:
- learning_rate: 0.001
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.15
- training_steps: 2000
- mixed_precision_training: Native AMP


### Framework versions

- Transformers 4.44.2
- Pytorch 2.4.0+cu121
- Datasets 3.0.0
- Tokenizers 0.19.1