Downloads · 30 days
5
22% of all-time downloads
whisper-tiny-sr-commonvoice-2000
cminja/whisper-tiny-sr-commonvoice-2000
whisper-tiny-sr-commonvoice-2000 is a automatic speech recognition model from cminja. Use it when you need speech turned into text. It is set up for transformers.
This model is a fine-tuned version of openai/whisper-tiny on Serbian Mozilla/Common Voice 13. It achieves the following results on the evaluation set:
All-time downloads
23
Public
Parameters
37.8M
151 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors151 MB · 99%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- Model type
- whisper
- Access
- Public
- Created
- Jun 21, 2024
- Updated
- Jun 21, 2024
- SHA
- d4f621bb
Model card
From the Hugging Face model README
finetuned whisper-tiny model on custom dataset
This model is a fine-tuned version of openai/whisper-tiny on Serbian Mozilla/Common Voice 13. It achieves the following results on the evaluation set:
- Loss: 0.1628
- Wer Ortho: 0.1635
- Wer: 0.0556
Training Procedure
Training Hyperparameters
The following hyperparameters were used during training:
- learning_rate: 3e-5
- train_batch_size: 32
- eval_batch_size: 32
- gradient_accumulation_steps: 2
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- training_steps: 2000
- mixed_precision_training: Native AMP
Training Results
| Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
|---|---|---|---|---|---|
| 0.0600 | 1.34 | 500 | 0.1852 | 0.1800 | 0.0745 |
| 0.0285 | 2.67 | 1000 | 0.1715 | 0.1710 | 0.0640 |
| 0.0140 | 4.01 | 1500 | 0.1658 | 0.1685 | 0.0582 |
Framework Versions
- Transformers: 4.41.2
- Pytorch: 2.3.0+cu121
- Datasets: 2.18.0
- Tokenizers: 0.19.1
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- whisper
- Created
- Jun 21, 2024
- Updated
- Jun 21, 2024