Modelpublic

yasalma/whisper-finetuned-tatartts-asr

sourceHugging Faceapache-2.0updated 5mo agoView on Hugging Face

0likes18downloads

Model Card

Whisper Fine-tuned ASR

This is a fine-tuned version of OpenAI Whisper for speech recognition.

Training

—Base model: openai/whisper-small
—Dataset: issai/TatarTTS

Fine-tuned using the notebook: https://github.com/Deep-unlearning/smol-audio/blob/master/FinetuneWhisper.ipynb

Usage

python

from transformers import pipeline

pipe = pipeline("automatic-speech-recognition", model="yasalma/whisper-finetuned-tatartts-asr")

result = pipe("audio.wav")
print(result["text"])