fengredrum/finetune-whisper-lora
Fine-Tune Whisper with Transformers and PEFT
Need to accurately convert spoken Cantonese or Mandarin into written text? This project helps improve existing speech-to-text models by training them with your specific audio data. You provide audio files and their corresponding transcripts, and it generates a specialized model that performs better on your unique accent or vocabulary. This is for language service providers, content creators, or researchers working with East Asian languages.
No commits in the last 6 months.
Use this if you need highly accurate transcriptions for Cantonese or Mandarin audio and off-the-shelf models aren't performing well enough on your specific datasets.
Not ideal if you're looking for a ready-to-use transcription tool without any technical setup or custom data training.
Stars
58
Forks
1
Language
Python
License
MIT
Category
Last pushed
Nov 04, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/fengredrum/finetune-whisper-lora"
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.