wav2vec2-common_voice-tamil
This model is a fine-tuned version of facebook/wav2vec2-large-xlsr-53 on the COMMON_VOICE - TA dataset. It achieves the following results on the evaluation set:
- Loss: 1.1172
- Wer: 1.0070
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
- 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_steps: 500
- num_epochs: 3.0
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| No log | 0.84 | 100 | 4.0148 | 1.0 |
| No log | 1.69 | 200 | 3.1738 | 1.0 |
| No log | 2.54 | 300 | 2.5980 | 1.0236 |
Framework versions
- Transformers 4.17.0.dev0
- Pytorch 1.10.1+cu113
- Datasets 1.18.1.dev0
- Tokenizers 0.10.3
- Downloads last month
- 14
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.