Santali_ASR-Model_KIIT2024_v1
This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3670
- Wer: 0.3788
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: 250
- num_epochs: 30
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 5.4585 | 3.7736 | 100 | 3.0474 | 1.0 |
| 2.5982 | 7.5472 | 200 | 1.2798 | 0.8776 |
| 0.6292 | 11.3208 | 300 | 0.3650 | 0.4523 |
| 0.2969 | 15.0943 | 400 | 0.3368 | 0.4148 |
| 0.1832 | 18.8679 | 500 | 0.3493 | 0.3986 |
| 0.1209 | 22.6415 | 600 | 0.3622 | 0.3833 |
| 0.0871 | 26.4151 | 700 | 0.3670 | 0.3788 |
Framework versions
- Transformers 4.42.0
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1
- Downloads last month
- 4
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
HF Inference API was unable to determine this model's library.
Model tree for DipsankarSinha/Santali_ASR-Model_KIIT2024_v1
Base model
facebook/wav2vec2-xls-r-300m