# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq
processor = AutoProcessor.from_pretrained("kosamit/whisper-tiny-ja-test")
model = AutoModelForSpeechSeq2Seq.from_pretrained("kosamit/whisper-tiny-ja-test", device_map="auto")Quick Links
whisper-tiny-ja-test
This model is a fine-tuned version of openai/whisper-tiny on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.6032
- Wer: 85.7143
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: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 10
- training_steps: 40
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 3.7501 | 3.33 | 10 | 1.6891 | 42.8571 |
| 0.6513 | 6.67 | 20 | 0.4518 | 85.7143 |
| 0.0104 | 10.0 | 30 | 0.5347 | 85.7143 |
| 0.0006 | 13.33 | 40 | 0.6032 | 85.7143 |
Framework versions
- Transformers 4.33.2
- Pytorch 2.1.1+cu118
- Datasets 2.16.1
- Tokenizers 0.13.3
- Downloads last month
- 4
Model tree for kosamit/whisper-tiny-ja-test
Base model
openai/whisper-tiny
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="kosamit/whisper-tiny-ja-test")