Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
Hebrew
whisper
whisper-event
Generated from Trainer
Eval Results (legacy)
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM
processor = AutoProcessor.from_pretrained("Shiry/whisper-large-v2-he")
model = AutoModelForMultimodalLM.from_pretrained("Shiry/whisper-large-v2-he")Quick Links
Whisper Large-V2 Hebrew
This model is a fine-tuned version of openai/whisper-large-v2 on the google/fleurs he_il dataset. It achieves the following results on the evaluation set:
- Loss: 0.5483
- Wer: 27
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: 64
- 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: 200
- mixed_precision_training: Native AMP
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu117
- Datasets 2.7.1.dev0
- Tokenizers 0.13.2
- Downloads last month
- 5
Dataset used to train Shiry/whisper-large-v2-he
Space using Shiry/whisper-large-v2-he 1
Evaluation results
- Wer on google/fleursself-reported27.000
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="Shiry/whisper-large-v2-he")