Automatic Speech Recognition
Transformers
PyTorch
Hebrew
whisper
whisper-event
Generated from Trainer
Eval Results (legacy)
# Load model directly
from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq
processor = AutoProcessor.from_pretrained("Shiry/Whisper_hebrew_medium")
model = AutoModelForSpeechSeq2Seq.from_pretrained("Shiry/Whisper_hebrew_medium")Quick Links
Whisper Medium Hebrew
This model is a fine-tuned version of openai/whisper-medium on the google/fleurs he_il dataset. It achieves the following results on the evaluation set:
- Wer: 34
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: 32
- eval_batch_size: 32
- 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: 5000
- 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_hebrew_medium
Evaluation results
- Wer on google/fleurs he_iltest set self-reported34.000
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="Shiry/Whisper_hebrew_medium")