Downloads · 30 days
5
3% of all-time downloads
whisper-tiny-finetuned-appen-dhc-20k
dhaval0108/whisper-tiny-finetuned-appen-dhc-20k
whisper-tiny-finetuned-appen-dhc-20k is a automatic speech recognition model from dhaval0108. 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
156
Public
Parameters
37.8M
151 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors151 MB · 96%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- License
- apache-2.0
- Model type
- whisper
- Access
- Public
- Created
- Jul 18, 2025
- Updated
- Jul 18, 2025
- SHA
- f3925870
Base models
Datasets
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"/>
whisper-tiny-finetuned-appen-dhc
This model is a fine-tuned version of openai/whisper-tiny on the whisper-tiny-finetune-appen-dhc dataset. It achieves the following results on the evaluation set:
- Loss: 0.4329
- Model Preparation Time: 0.0045
- Wer: 0.2818
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: 8
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Model Preparation Time | Wer |
|---|---|---|---|---|---|
| 0.4812 | 1.0 | 250 | 0.4305 | 0.0045 | 0.2802 |
| 0.3618 | 2.0 | 500 | 0.5207 | 0.0045 | 0.2744 |
| 0.2855 | 3.0 | 750 | 0.4534 | 0.0045 | 0.2352 |
| 0.1908 | 4.0 | 1000 | 0.4328 | 0.0045 | 0.2330 |
| 0.1289 | 5.0 | 1250 | 0.4196 | 0.0045 | 0.2307 |
| 0.08 | 6.0 | 1500 | 0.4295 | 0.0045 | 0.1950 |
| 0.0434 | 7.0 | 1750 | 0.4446 | 0.0045 | 0.1776 |
| 0.0169 | 7.9685 | 1992 | 0.4745 | 0.0045 | 0.1689 |
Framework versions
- Transformers 4.48.3
- Pytorch 2.5.1+cu124
- Datasets 3.2.0
- Tokenizers 0.21.2
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- whisper
- License
- apache-2.0
- Languages
- en
- Created
- Jul 18, 2025
- Updated
- Jul 18, 2025