Vardis/Whisper-Medium-Greek

Fine-Tuned Whisper Medium

This is a Medium-sized Whisper model fine-tuned for improved transcription performance. It has 764M parameters and achieves the following WER (Word Error Rate) metrics on the evaluation set:

• WER: 16.17
• CER: 7.16

Model Details

• Model Type: Whisper (Medium)
• Fine-tuned From: OpenAI Whisper Medium
• Language(s): Greek

Intended Use

This model is designed for automatic speech recognition (ASR) tasks. It can be used to transcribe audio into text efficiently.

How to Use

from transformers import WhisperProcessor, WhisperForConditionalGeneration
from peft import PeftModel
import torch

device = "cuda" if torch.cuda.is_available() else "cpu"

# Load base model and Greek fine-tuned LoRA weights
base_model = WhisperForConditionalGeneration.from_pretrained("openai/whisper-medium").to(device)
model = PeftModel.from_pretrained(base_model, "Vardis/Whisper-Medium-Greek").to(device)
processor = WhisperProcessor.from_pretrained("Vardis/Whisper-Medium-Greek")

# Load your audio waveform (e.g., using librosa or torchaudio)
audio_input = ...  

# Generate transcription
inputs = processor(audio_input, return_tensors="pt").input_features.to(device)
predicted_ids = model.generate(inputs)
transcription = processor.batch_decode(predicted_ids, skip_special_tokens=True)

print(transcription)

Context / Reference

This model was developed as part of the work described in:

Georgilas, V., Stafylakis, T. (2025). Automatic Speech Recognition for Greek Medical Dictation.
The paper focuses on Greek medical ASR research in general and is not primarily about the model itself, but provides context for its development. Users are welcome to use the model freely for research and practical applications.

BibTeX citation:

@misc{georgilas2025greekasr,
  title={Automatic Speech Recognition for Greek Medical Dictation},
  author={Vardis Georgilas and Themos Stafylakis},
  year={2025},
  note={Available at: https://www.arxiv.org/abs/2509.23550}
}