# Load model directly
from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq
processor = AutoProcessor.from_pretrained("Kohn-AI/yi-whisper-large-v3-omnilingual-v1")
model = AutoModelForSpeechSeq2Seq.from_pretrained("Kohn-AI/yi-whisper-large-v3-omnilingual-v1")Quick Links
yi-whisper-large-v3-omnilingual-v1
This model is a fine-tuned version of ivrit-ai/yi-whisper-large-v3 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3867
- Wer Ortho: 0.3832
- Wer: 0.3101
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: 2
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 32
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: constant_with_warmup
- lr_scheduler_warmup_ratio: 0.1
- lr_scheduler_warmup_steps: 100
- num_epochs: 4
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
|---|---|---|---|---|---|
| 0.2433 | 1.6446 | 100 | 0.3473 | 0.3845 | 0.3281 |
| 0.1093 | 3.2810 | 200 | 0.3867 | 0.3832 | 0.3101 |
Framework versions
- Transformers 4.48.1
- Pytorch 2.4.0
- Datasets 3.6.0
- Tokenizers 0.21.4
- Downloads last month
- 164
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="Kohn-AI/yi-whisper-large-v3-omnilingual-v1")