Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
Chinese
whisper
Generated from Trainer
Instructions to use VingeNie/whisper-tiny-zh_CN_lr4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use VingeNie/whisper-tiny-zh_CN_lr4 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="VingeNie/whisper-tiny-zh_CN_lr4")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("VingeNie/whisper-tiny-zh_CN_lr4") model = AutoModelForSpeechSeq2Seq.from_pretrained("VingeNie/whisper-tiny-zh_CN_lr4", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Whisper Tiny chinese - VingeNie
This model is a fine-tuned version of openai/whisper-tiny on the Common Voice 16.1 dataset. It achieves the following results on the evaluation set:
- Loss: 0.7223
- Cer Ortho: 40.6344
- Cer: 29.5803
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: 0.0001
- train_batch_size: 64
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant_with_warmup
- lr_scheduler_warmup_steps: 25
- training_steps: 650
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Cer Ortho | Cer |
|---|---|---|---|---|---|
| 0.7743 | 0.3594 | 225 | 0.7942 | 40.4431 | 31.4481 |
| 0.7344 | 0.7188 | 450 | 0.7223 | 40.6344 | 29.5803 |
Framework versions
- Transformers 4.40.1
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1
- Downloads last month
- 4
Model tree for VingeNie/whisper-tiny-zh_CN_lr4
Base model
openai/whisper-tiny