Downloads · 30 days
7
3% of all-time downloads
whisper-medium-zh
angliu/whisper-medium-zh
whisper-medium-zh is a automatic speech recognition model from angliu. 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
207
Public
Parameters
764M
3.1 GB on disk
Likes
1
Public
Repo makeup
Click a slice to open those files.
.safetensors3.1 GB · 100%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- License
- apache-2.0
- Model type
- whisper
- Access
- Public
- Created
- Jul 31, 2024
- Updated
- Jul 31, 2024
- SHA
- 335cb1eb
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 zh - xh camera
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: 1.9979
- Wer: 100.0
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: 8
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 50
- num_epochs: 1
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.0876 | 0.16 | 100 | 1.9884 | 100.0 |
| 0.0627 | 0.32 | 200 | 1.9451 | 100.0 |
| 0.0674 | 0.48 | 300 | 2.0586 | 100.0 |
| 0.0772 | 0.64 | 400 | 1.9965 | 100.0 |
| 0.0676 | 0.8 | 500 | 2.0561 | 100.0 |
| 0.0666 | 0.96 | 600 | 1.9979 | 100.0 |
Framework versions
- Transformers 4.42.3
- Pytorch 2.4.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- whisper
- License
- apache-2.0
- Languages
- zh
- Created
- Jul 31, 2024
- Updated
- Jul 31, 2024