Downloads · 30 days
10
32% of all-time downloads
whisper-medium-en-cv-4.8
xbilek25/whisper-medium-en-cv-4.8
whisper-medium-en-cv-4.8 is a automatic speech recognition model from xbilek25. 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
31
Public
Parameters
764M
18.3 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors3.1 GB · 100%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- License
- apache-2.0
- Model type
- whisper
- Access
- Public
- Created
- May 3, 2025
- Updated
- May 3, 2025
- SHA
- 97a1b936
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. -->
whisper-medium-en-cv-4.9
This model is a fine-tuned version of openai/whisper-medium.en on the Common Voice 17.0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.3518
- Wer: 11.3793
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: 8e-06
- train_batch_size: 48
- eval_batch_size: 4
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH 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: 150
- training_steps: 1500
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| No log | 0 | 0 | 1.5197 | 12.4138 |
| 0.2372 | 0.2 | 300 | 0.3762 | 11.8966 |
| 0.3158 | 0.4 | 600 | 0.3572 | 11.5517 |
| 0.0923 | 1.1 | 900 | 0.3600 | 12.0690 |
| 0.0935 | 1.3 | 1200 | 0.3583 | 12.4138 |
| 0.1502 | 1.5 | 1500 | 0.3518 | 11.3793 |
Framework versions
- Transformers 4.51.3
- Pytorch 2.6.0+cu124
- Datasets 3.5.1
- Tokenizers 0.21.1
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- whisper
- License
- apache-2.0
- Languages
- en
- Created
- May 3, 2025
- Updated
- May 3, 2025