Downloads · 30 days
13
29% of all-time downloads
ap-i5JeeZWT4XT69p4xD3MpUA
mdsingh2024/ap-i5JeeZWT4XT69p4xD3MpUA
ap-i5JeeZWT4XT69p4xD3MpUA 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
45
Public
Parameters
242M
9.7 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors967 MB · 99%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- License
- apache-2.0
- Model type
- whisper
- Access
- Public
- Created
- Feb 13, 2025
- Updated
- Feb 13, 2025
- SHA
- 6ced21ca
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"/>
ap-i5JeeZWT4XT69p4xD3MpUA
This model is a fine-tuned version of openai/whisper-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 3.4341
- Model Preparation Time: 0.0064
- Wer: 0.9964
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: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Model Preparation Time | Wer |
|---|---|---|---|---|---|
| 0.0882 | 1.0 | 56 | 1.1967 | 0.0064 | 0.5404 |
| 0.0503 | 2.0 | 112 | 1.3110 | 0.0064 | 0.6217 |
| 0.0396 | 3.0 | 168 | 1.4180 | 0.0064 | 0.6232 |
| 0.0562 | 4.0 | 224 | 1.6773 | 0.0064 | 0.7554 |
| 0.0527 | 5.0 | 280 | 2.0603 | 0.0064 | 0.9328 |
| 0.0464 | 6.0 | 336 | 2.5807 | 0.0064 | 0.9055 |
| 0.0498 | 7.0 | 392 | 3.0902 | 0.0064 | 1.1502 |
| 0.0272 | 8.0 | 448 | 3.6158 | 0.0064 | 1.1303 |
| 0.0021 | 9.0 | 504 | 3.3782 | 0.0064 | 0.9853 |
| 0.0003 | 9.8288 | 550 | 3.4341 | 0.0064 | 0.9964 |
Framework versions
- Transformers 4.48.3
- Pytorch 2.5.1+cu124
- Datasets 3.2.0
- Tokenizers 0.21.0
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- whisper
- License
- apache-2.0
- Created
- Feb 13, 2025
- Updated
- Feb 13, 2025