naver/multilingual-distilwhisper
This repository contains all the code necessary for running the multilingual distilwhisper from Ferraz et al. 2024 IEEE ICASSP paper.
This project helps create highly accurate automated speech recognition (ASR) systems for specific languages. It takes audio input and outputs transcribed text, focusing on improving performance for less common or niche languages. It's designed for machine learning engineers or researchers building speech-to-text applications where precision in diverse languages is critical.
Use this if you need to improve the accuracy of speech-to-text transcription for a specific language beyond what general multilingual models typically offer.
Not ideal if you primarily work with common languages where general ASR models already perform well, or if you don't have the technical expertise to train and fine-tune machine learning models.
Stars
33
Forks
—
Language
Python
License
—
Category
Last pushed
Oct 23, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/naver/multilingual-distilwhisper"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
YuanGongND/whisper-at
Code and Pretrained Models for Interspeech 2023 Paper "Whisper-AT: Noise-Robust Automatic Speech...
adi-gov-tw/Taiwan-Tongues-ASR-CE
Taiwan Tongues ASR CE 是一個開源語音辨識（Automatic Speech Recognition, ASR）模型專案，專為台灣多元語言環境設計。 本模型支援...
huggingface/distil-whisper
Distilled variant of Whisper for speech recognition. 6x faster, 50% smaller, within 1% word error rate.
phineas-pta/fine-tune-whisper-vi
jupyter notebooks to fine tune whisper models on Vietnamese using Colab and/or Kaggle and/or AWS EC2
KevKibe/African-Whisper
🚀 Framework for seamless fine-tuning of Whisper model on a multi-lingual dataset and deployment to prod.