Downloads · 30 days
31
7% of all-time downloads
whisper-large-v3-turbo-cantonese
wingskh/whisper-large-v3-turbo-cantonese
whisper-large-v3-turbo-cantonese is a automatic speech recognition model from wingskh. Use it when you need speech turned into text. It is set up for transformers. The card lists the license as mit.
should probably proofread and complete it, then remove this comment. --
All-time downloads
455
Public
Parameters
809M
19.4 GB on disk
Likes
1
Public
Repo makeup
Click a slice to open those files.
.safetensors3.2 GB · 100%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- License
- mit
- Model type
- whisper
- Access
- Public
- Created
- Oct 28, 2024
- Updated
- Nov 17, 2024
- SHA
- 5e4a911e
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-large-v3-turbo-cantonese-10
This model is a fine-tuned version of openai/whisper-large-v3-turbo on the mozilla-foundation/common_voice_16_0 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: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Use 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: 10
- training_steps: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| No log | 0.0114 | 10 | 0.7841 | 90.9188 |
Framework versions
- Transformers 4.47.0.dev0
- Pytorch 2.5.1+cu121
- Datasets 3.0.2
- Tokenizers 0.20.1
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- whisper
- License
- mit
- Languages
- zh
- Created
- Oct 28, 2024
- Updated
- Nov 17, 2024