Downloads · 30 days
8
13% of all-time downloads
whisper-medium-vi-cv
Scrya/whisper-medium-vi-cv
whisper-medium-vi-cv is a automatic speech recognition model from Scrya. 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
61
Public
Repo size
21.4 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin3.1 GB · 100%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- License
- apache-2.0
- Model type
- whisper
- Access
- Public
- Created
- Dec 18, 2022
- Updated
- Dec 19, 2022
- SHA
- af3547ba
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 VI - CV - Augmented
This model is a fine-tuned version of openai/whisper-medium on the Common Voice 11.0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.6613
- Wer: 18.0303
- Cer: 8.3095
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: 32
- eval_batch_size: 16
- 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: 5000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
|---|---|---|---|---|---|
| 0.0053 | 11.49 | 1000 | 0.5429 | 18.1290 | 8.4643 |
| 0.0021 | 22.99 | 2000 | 0.5916 | 18.8857 | 8.6538 |
| 0.0001 | 34.48 | 3000 | 0.6348 | 18.3374 | 8.4296 |
| 0.0001 | 45.98 | 4000 | 0.6508 | 17.9754 | 8.3149 |
| 0.0001 | 57.47 | 5000 | 0.6613 | 18.0303 | 8.3095 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.1+cu117
- Datasets 2.7.1.dev0
- Tokenizers 0.13.2
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- whisper
- License
- apache-2.0
- Languages
- vi
- Created
- Dec 18, 2022
- Updated
- Dec 19, 2022