wav2vec2-mms-1b-CV17.0
This model is a fine-tuned version of 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
- Downloads last month
- 17
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.
Model tree for ndeclarke/wav2vec2-mms-1b-CV17.0
Base model
facebook/mms-1b-allEvaluation results
- Wer on common_voice_17_0self-reported0.654
- Bleu on common_voice_17_0self-reported0.142