Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
Korean
whisper
hf-asr-leaderboard
Generated from Trainer
# Load model directly
from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq
processor = AutoProcessor.from_pretrained("xppast/voice")
model = AutoModelForSpeechSeq2Seq.from_pretrained("xppast/voice")Quick Links
jinkrsmodel
This model is a fine-tuned version of openai/whisper-base on the xppast/voice dataset. It achieves the following results on the evaluation set:
- Loss: 1.6485
- Cer: 40.4444
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: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 400
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Cer |
|---|---|---|---|---|
| 0.0146 | 33.33 | 100 | 1.4532 | 35.5556 |
| 0.0034 | 66.67 | 200 | 1.5364 | 40.8889 |
| 0.0013 | 100.0 | 300 | 1.5890 | 41.3333 |
| 0.0007 | 133.33 | 400 | 1.6485 | 40.4444 |
Framework versions
- Transformers 4.36.0.dev0
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0
- Downloads last month
- 5
Model tree for xppast/voice
Base model
openai/whisper-base
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="xppast/voice")