Downloads · 30 days
5
21% of all-time downloads
whisper-small-hi-custom4
PradyumSomebody/whisper-small-hi-custom4
whisper-small-hi-custom4 is a automatic speech recognition model from PradyumSomebody. 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
24
Public
Parameters
242M
23.2 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors967 MB · 100%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- License
- apache-2.0
- Model type
- whisper
- Access
- Public
- Created
- Jul 17, 2024
- Updated
- Jul 22, 2024
- SHA
- 0d3dde4e
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. -->
Whisper Small EN - Pradyum Agarwal 4
This model is a fine-tuned version of openai/whisper-small on the Audio Medical Combined Dataset dataset. It achieves the following results on the evaluation set:
- Loss: 0.0009
- Wer: 0.0
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: 1e-05
- train_batch_size: 10
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 500
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.749 | 0.5556 | 25 | 0.8143 | 17.9088 |
| 0.6168 | 1.1111 | 50 | 0.6651 | 14.0483 |
| 0.4324 | 1.6667 | 75 | 0.3085 | 12.4397 |
| 0.1351 | 2.2222 | 100 | 0.1857 | 8.6863 |
| 0.1415 | 2.7778 | 125 | 0.1252 | 5.3083 |
| 0.0638 | 3.3333 | 150 | 0.0826 | 2.6810 |
| 0.053 | 3.8889 | 175 | 0.0494 | 1.7694 |
| 0.0303 | 4.4444 | 200 | 0.0282 | 0.9115 |
| 0.0252 | 5.0 | 225 | 0.0155 | 0.5362 |
| 0.012 | 5.5556 | 250 | 0.0111 | 0.4826 |
| 0.0119 | 6.1111 | 275 | 0.0051 | 0.1072 |
| 0.0029 | 6.6667 | 300 | 0.0035 | 0.0 |
| 0.0043 | 7.2222 | 325 | 0.0030 | 0.0536 |
| 0.0051 | 7.7778 | 350 | 0.0032 | 0.0536 |
| 0.0015 | 8.3333 | 375 | 0.0020 | 0.0 |
| 0.0013 | 8.8889 | 400 | 0.0016 | 0.0 |
| 0.001 | 9.4444 | 425 | 0.0015 | 0.0 |
| 0.0015 | 10.0 | 450 | 0.0011 | 0.0 |
| 0.0008 | 10.5556 | 475 | 0.0010 | 0.0 |
| 0.0007 | 11.1111 | 500 | 0.0009 | 0.0 |
Framework versions
- Transformers 4.42.4
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- whisper
- License
- apache-2.0
- Languages
- en
- Created
- Jul 17, 2024
- Updated
- Jul 22, 2024