Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
Romanian
whisper
Generated from Trainer
# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq
processor = AutoProcessor.from_pretrained("iRaduS/whisper-memory-efficient")
model = AutoModelForSpeechSeq2Seq.from_pretrained("iRaduS/whisper-memory-efficient", device_map="auto")Quick Links
Whisper Large v3 RO - finetune
This model is a fine-tuned version of openai/whisper-large-v3 on the custom dataset.
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: 8
- seed: 42
- gradient_accumulation_steps: 32
- total_train_batch_size: 256
- 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: linear
- lr_scheduler_warmup_steps: 10
- num_epochs: 8
- mixed_precision_training: Native AMP
Training results
Framework versions
- Transformers 4.48.0
- Pytorch 2.7.1+cu126
- Datasets 4.0.0
- Tokenizers 0.21.2
- Downloads last month
- 7
Model tree for iRaduS/whisper-memory-efficient
Base model
openai/whisper-large-v3
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="iRaduS/whisper-memory-efficient")