wav2vec2-large-xlsr-53-Bangla-Common_Voice
This model is a fine-tuned version of facebook/wav2vec2-large-xlsr-53 on the common_voice_11_0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.6172
- Wer: 0.6577
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: 0.001
- train_batch_size: 24
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 48
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 15
Training results
Training Loss | Epoch | Step | Validation Loss | Wer |
---|---|---|---|---|
2.922 | 4.57 | 800 | 0.7379 | 0.8157 |
0.5136 | 9.14 | 1600 | 0.6155 | 0.7056 |
0.2759 | 13.71 | 2400 | 0.6172 | 0.6577 |
Framework versions
- Transformers 4.24.0
- Pytorch 1.13.1+cu116
- Datasets 2.11.0
- Tokenizers 0.13.2
- Downloads last month
- 5,047
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.