Downloads · 30 days
6
2% of all-time downloads
whisper-small-singlish_augmented_again_1200steps
yy1412/whisper-small-singlish_augmented_again_1200steps
whisper-small-singlish_augmented_again_1200steps is a automatic speech recognition model from yy1412. 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
320
Public
Repo size
4.8 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin967 MB · 100%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- License
- apache-2.0
- Model type
- whisper
- Access
- Public
- Created
- May 29, 2023
- Updated
- May 30, 2023
- SHA
- ada43f91
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-singlish_augmented_again_1200steps
This model is a fine-tuned version of yy1412/whisper-small-singlish_augmented on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0075
- Wer: 0.4993
This model is trained on properly augmented dataset
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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- training_steps: 1200
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.0204 | 0.75 | 300 | 0.0116 | 0.5917 |
| 0.0047 | 1.5 | 600 | 0.0081 | 0.3513 |
| 0.001 | 2.25 | 900 | 0.0073 | 0.3698 |
| 0.0007 | 3.0 | 1200 | 0.0075 | 0.4993 |
Framework versions
- Transformers 4.29.2
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- whisper
- License
- apache-2.0
- Created
- May 29, 2023
- Updated
- May 30, 2023