Downloads · 30 days
52
4% of all-time downloads
wav2vec2-60-urdu
kingabzpro/wav2vec2-60-urdu
wav2vec2-60-urdu is a automatic speech recognition model from kingabzpro. Use it when you need speech turned into text. It is set up for transformers. The card lists the license as apache-2.0.
🔴Check out my latest URDU ASR model with 25 WER here - kingabzpro/whisper-large-v3-turbo-urdu
All-time downloads
1.2K
Public
Parameters
94.4M
15 GB on disk
Likes
1
Public
Repo makeup
Click a slice to open those files.
.bin378 MB · 50%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- License
- apache-2.0
- Model type
- wav2vec2
- Access
- Public
- Created
- Mar 2, 2022
- Updated
- Jul 5, 2025
- SHA
- 7624fb67
Model card
From the Hugging Face model README
🔴Check out my latest URDU ASR model with 25 WER here -> kingabzpro/whisper-large-v3-turbo-urdu
wav2vec2-large-xlsr-53-urdu
This model is a fine-tuned version of Harveenchadha/vakyansh-wav2vec2-urdu-urm-60 on the common_voice dataset. It achieves the following results on the evaluation set:
- Wer: 0.5913
- Cer: 0.3310
Model description
The training and valid dataset is 0.58 hours. It was hard to train any model on lower number of so I decided to take vakyansh-wav2vec2-urdu-urm-60 checkpoint and finetune the wav2vec2 model.
Training procedure
Trained on Harveenchadha/vakyansh-wav2vec2-urdu-urm-60 due to lesser number of samples.
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: 200
- num_epochs: 50
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
|---|---|---|---|---|---|
| 12.6045 | 8.33 | 100 | 8.4997 | 0.6978 | 0.3923 |
| 1.3367 | 16.67 | 200 | 5.0015 | 0.6515 | 0.3556 |
| 0.5344 | 25.0 | 300 | 9.3687 | 0.6393 | 0.3625 |
| 0.2922 | 33.33 | 400 | 9.2381 | 0.6236 | 0.3432 |
| 0.1867 | 41.67 | 500 | 6.2150 | 0.6035 | 0.3448 |
| 0.1166 | 50.0 | 600 | 6.4496 | 0.5913 | 0.3310 |
Framework versions
- Transformers 4.15.0
- Pytorch 1.10.0+cu111
- Datasets 1.17.0
- Tokenizers 0.10.3
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- wav2vec2
- License
- apache-2.0
- Languages
- ur
- Created
- Mar 2, 2022
- Updated
- Jul 5, 2025