Downloads · 30 days
1
2% of all-time downloads
whisper-medium-attempt1
shreyasdesaisuperU/whisper-medium-attempt1
whisper-medium-attempt1 is a automatic speech recognition model from shreyasdesaisuperU. 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
764M
134 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt61 GB · 62%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- License
- apache-2.0
- Model type
- whisper
- Access
- Public
- Created
- Nov 7, 2024
- Updated
- Dec 3, 2024
- SHA
- 3feed35c
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 SSD superU
This model is a fine-tuned version of openai/whisper-medium on the None dataset. It achieves the following results on the evaluation set:
- Loss: 4.5612
- Wer: 187.8716
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: 16
- eval_batch_size: 8
- 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: 500
- training_steps: 2000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 1.8855 | 3.125 | 100 | 2.7949 | 127.8716 |
| 1.2923 | 6.25 | 200 | 2.9861 | 141.1486 |
| 0.672 | 9.375 | 300 | 3.3083 | 125.4054 |
| 0.2436 | 12.5 | 400 | 3.6404 | 117.5676 |
| 0.1134 | 15.625 | 500 | 3.7910 | 123.9189 |
| 0.0619 | 18.75 | 600 | 3.7506 | 166.3176 |
| 0.0465 | 21.875 | 700 | 3.8297 | 116.4527 |
| 0.0302 | 25.0 | 800 | 3.9483 | 140.3716 |
| 0.0253 | 28.125 | 900 | 4.0462 | 117.8378 |
| 0.0122 | 31.25 | 1000 | 4.1690 | 118.3784 |
| 0.0092 | 34.375 | 1100 | 4.2067 | 142.2297 |
| 0.0048 | 37.5 | 1200 | 4.3142 | 149.9324 |
| 0.002 | 40.625 | 1300 | 4.4275 | 176.7230 |
| 0.0013 | 43.75 | 1400 | 4.3985 | 174.0203 |
| 0.0005 | 46.875 | 1500 | 4.4872 | 173.1081 |
| 0.0005 | 50.0 | 1600 | 4.5157 | 171.8919 |
| 0.0004 | 53.125 | 1700 | 4.5372 | 184.1216 |
| 0.0003 | 56.25 | 1800 | 4.5506 | 185.2703 |
| 0.0003 | 59.375 | 1900 | 4.5583 | 185.4054 |
| 0.0003 | 62.5 | 2000 | 4.5612 | 187.8716 |
Framework versions
- Transformers 4.46.2
- Pytorch 2.5.1+cu124
- Datasets 3.1.0
- Tokenizers 0.20.3
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- whisper
- License
- apache-2.0
- Created
- Nov 7, 2024
- Updated
- Dec 3, 2024