Downloads · 30 days
6
9% of all-time downloads
indicwav2vec-assamese-asr
bijaykumarsingh/indicwav2vec-assamese-asr
indicwav2vec-assamese-asr is a automatic speech recognition model from bijaykumarsingh. Use it when you need speech turned into text. It is set up for transformers.
should probably proofread and complete it, then remove this comment. --
All-time downloads
70
Public
Parameters
316M
2.5 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors1.3 GB · 100%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- Model type
- wav2vec2
- Access
- Public
- Created
- May 19, 2026
- Updated
- May 21, 2026
- SHA
- 8485f93d
Base models
Model card
From the Hugging Face model README
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
indicwav2vec-assamese-asr
This model is a fine-tuned version of anuragshas/wav2vec2-large-xlsr-as on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.5665
- Wer: 0.5398
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: 1e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 5000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 1.1178 | 0.4568 | 500 | 0.7252 | 0.6090 |
| 1.0189 | 0.9137 | 1000 | 0.6767 | 0.5898 |
| 1.0088 | 1.3705 | 1500 | 0.6489 | 0.5756 |
| 0.9925 | 1.8273 | 2000 | 0.6216 | 0.5655 |
| 0.9547 | 2.2841 | 2500 | 0.6037 | 0.5563 |
| 0.9475 | 2.7410 | 3000 | 0.5900 | 0.55 |
| 0.9093 | 3.1978 | 3500 | 0.5794 | 0.5460 |
| 0.957 | 3.6546 | 4000 | 0.5727 | 0.5443 |
| 0.8822 | 4.1115 | 4500 | 0.5681 | 0.5405 |
| 0.8718 | 4.5683 | 5000 | 0.5665 | 0.5395 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.4.0+cu121
- Datasets 3.1.0
- Tokenizers 0.20.3
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- wav2vec2
- Created
- May 19, 2026
- Updated
- May 21, 2026