yeyupiaoling/Whisper-Finetune
Fine-tuning framework for OpenAI's Whisper speech-to-text model with LoRA, supporting multiple training modes and accelerated inference via CTranslate2 and GGML.
Not currently ranked — collecting fresh signals.
star history
This project provides tools to fine-tune Whisper models using LoRA for efficient adaptation. It supports training on data with or without timestamps, and even on non-speech audio. The repository includes utilities for accelerating inference using CTranslate2 and GGML backends, enabling deployment on web interfaces, Windows desktop applications, and Android devices. Multiple Whisper model sizes from tiny to large-v3 are supported.
Frequently asked
- What is yeyupiaoling/Whisper-Finetune?
- Fine-tuning framework for OpenAI's Whisper speech-to-text model with LoRA, supporting multiple training modes and accelerated inference via CTranslate2 and GGML.
- Is Whisper-Finetune open source?
- Yes — yeyupiaoling/Whisper-Finetune is open source, released under the Apache-2.0 license.
- What language is Whisper-Finetune written in?
- yeyupiaoling/Whisper-Finetune is primarily written in C.
- How popular is Whisper-Finetune?
- yeyupiaoling/Whisper-Finetune has 1.2k stars on GitHub.
- Where can I find Whisper-Finetune?
- yeyupiaoling/Whisper-Finetune is on GitHub at https://github.com/yeyupiaoling/Whisper-Finetune.