Downloads · 30 days
3
2% of all-time downloads
ap-jJtnUuCDSWoPRGfeHin63v
mdsingh2024/ap-jJtnUuCDSWoPRGfeHin63v
ap-jJtnUuCDSWoPRGfeHin63v is a automatic speech recognition model from mdsingh2024. 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
195
Public
Parameters
72.6M
7 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors290 MB · 98%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- License
- apache-2.0
- Model type
- whisper
- Access
- Public
- Created
- Jul 14, 2025
- Updated
- Jul 14, 2025
- SHA
- d1d561ec
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. -->
<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/> <img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/> <img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/> <img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>
ap-jJtnUuCDSWoPRGfeHin63v
This model is a fine-tuned version of openai/whisper-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.5358
- Model Preparation Time: 0.0034
- Wer: 0.1536
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: 0.0003
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 64
- 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: 400
- num_epochs: 12
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Model Preparation Time | Wer |
|---|---|---|---|---|---|
| 0.8691 | 1.0 | 13 | 1.5917 | 0.0034 | 0.2712 |
| 0.2972 | 2.0 | 26 | 0.5042 | 0.0034 | 0.2033 |
| 0.1803 | 3.0 | 39 | 0.2986 | 0.0034 | 0.1344 |
| 0.0644 | 4.0 | 52 | 0.2942 | 0.0034 | 0.1340 |
| 0.039 | 5.0 | 65 | 0.3091 | 0.0034 | 0.1438 |
| 0.0077 | 6.0 | 78 | 0.4169 | 0.0034 | 0.1438 |
| 0.0165 | 7.0 | 91 | 0.4288 | 0.0034 | 0.1513 |
| 0.0439 | 8.0 | 104 | 0.4070 | 0.0034 | 0.1678 |
| 0.047 | 9.0 | 117 | 0.4040 | 0.0034 | 0.1503 |
| 0.0078 | 10.0 | 130 | 0.3851 | 0.0034 | 0.1438 |
| 0.0408 | 11.0 | 143 | 0.5641 | 0.0034 | 0.1601 |
| 0.1048 | 11.08 | 144 | 0.5358 | 0.0034 | 0.1536 |
Framework versions
- Transformers 4.48.3
- Pytorch 2.5.1+cu124
- Datasets 3.2.0
- Tokenizers 0.21.1
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- whisper
- License
- apache-2.0
- Created
- Jul 14, 2025
- Updated
- Jul 14, 2025