config-3
This model is a fine-tuned version of DrishtiSharma/wav2vec2-large-xls-r-300m-hi-CV7 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 3.1887
- Wer: 1.0
- Cer: 0.9380
- Mer: 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: 0.0004
- 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: 100
- num_epochs: 40
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer | Mer |
|---|---|---|---|---|---|---|
| 7.6508 | 1.0050 | 100 | 3.5149 | 1.0 | 1.0 | 1.0 |
| 3.4168 | 2.0101 | 200 | 3.4249 | 1.0 | 0.9394 | 1.0 |
| 3.3519 | 3.0151 | 300 | 3.3553 | 0.9997 | 0.9536 | 0.9997 |
| 3.2964 | 4.0201 | 400 | 3.1887 | 1.0 | 0.9380 | 1.0 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1
- Downloads last month
- 11
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.