Downloads · 30 days
22
2% of all-time downloads
whisper-small-urdu
Abdullah17/whisper-small-urdu
whisper-small-urdu is a automatic speech recognition model from Abdullah17. 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
1.4K
Public
Repo size
2.9 GB
Likes
4
Public
Repo makeup
Click a slice to open those files.
.bin967 MB · 100%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- License
- apache-2.0
- Model type
- whisper
- Access
- Public
- Created
- Nov 22, 2022
- Updated
- Dec 13, 2022
- SHA
- e9849e36
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. -->
Whisper Small UR - Muhammad Abdullah
This model is a fine-tuned version of openai/whisper-Small on the Common Voice 11.0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.9758
- Wer: 41.6987
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 10
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 3500
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.0074 | 9.62 | 1000 | 0.8238 | 42.0345 |
| 0.0003 | 19.23 | 2000 | 0.9381 | 42.6583 |
| 0.0002 | 28.85 | 3000 | 0.9758 | 41.6987 |
Framework versions
- Transformers 4.25.0.dev0
- Pytorch 1.12.1+cu113
- Datasets 2.7.0
- Tokenizers 0.13.2
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- whisper
- License
- apache-2.0
- Languages
- ur
- Created
- Nov 22, 2022
- Updated
- Dec 13, 2022