Downloads · 30 days
2
6% of all-time downloads
wav2vec2-base-garhwali-demo-google-colab
akritidhasmana/wav2vec2-base-garhwali-demo-google-colab
wav2vec2-base-garhwali-demo-google-colab is a automatic speech recognition model from akritidhasmana. Use it when you need speech turned into text. It is set up for transformers. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
35
Public
Parameters
94.5M
378 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors378 MB · 100%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- License
- apache-2.0
- Model type
- wav2vec2
- Access
- Public
- Created
- Sep 19, 2025
- Updated
- Sep 19, 2025
- SHA
- 0abad43e
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. -->
wav2vec2-base-garhwali-demo-google-colab
This model is a fine-tuned version of facebook/wav2vec2-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.5756
- Wer: 0.7689
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: 0.0001
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- 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: 1000
- num_epochs: 30
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 5.0079 | 2.2321 | 500 | 3.3153 | 1.0 |
| 2.7173 | 4.4643 | 1000 | 1.8583 | 0.9674 |
| 1.6533 | 6.6964 | 1500 | 1.4112 | 0.8627 |
| 1.2519 | 8.9286 | 2000 | 1.2894 | 0.8331 |
| 1.0268 | 11.1607 | 2500 | 1.3173 | 0.7906 |
| 0.8764 | 13.3929 | 3000 | 1.3444 | 0.8009 |
| 0.7523 | 15.625 | 3500 | 1.3973 | 0.7838 |
| 0.663 | 17.8571 | 4000 | 1.4064 | 0.7877 |
| 0.5775 | 20.0893 | 4500 | 1.4676 | 0.7840 |
| 0.5175 | 22.3214 | 5000 | 1.5052 | 0.7707 |
| 0.469 | 24.5536 | 5500 | 1.5215 | 0.7618 |
| 0.4194 | 26.7857 | 6000 | 1.5784 | 0.7633 |
| 0.4031 | 29.0179 | 6500 | 1.5756 | 0.7689 |
Framework versions
- Transformers 4.56.1
- Pytorch 2.8.0+cu126
- Datasets 4.0.0
- Tokenizers 0.22.0
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- wav2vec2
- License
- apache-2.0
- Created
- Sep 19, 2025
- Updated
- Sep 19, 2025