biodatlab/thonburian-whisper
Thonburian Whisper: Open models for fine-tuned Whisper in Thai. Try our demo on Huggingface space:
This project offers tools to convert spoken Thai into written text accurately, even when there's background noise or specific vocabulary from fields like finance or medicine. It takes Thai audio recordings, like interviews or voicemails, and produces a written transcript. Anyone needing to process Thai speech, such as content creators, researchers, or business analysts, would find this useful for tasks like subtitling or documentation.
186 stars. No commits in the last 6 months.
Use this if you need to reliably transcribe Thai audio into text, especially if the audio contains domain-specific language or environmental noise.
Not ideal if your primary need is for precise timestamping with the highest accuracy, as dedicated timestamp models might have slightly lower overall transcription accuracy.
Stars
186
Forks
20
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Jul 29, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/biodatlab/thonburian-whisper"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
Arkapravo-Ghosh/speech-to-text
Speech to Text Transcription using OpenAI Whisper v3 and FastAPI
scalable-ml-deep-learning/fine_tune_whisper
Fine-Tune Whisper for Italian ASR with transformers
Arnav-Sharmaa/Multilingual-Speech-to-Text-and-Speech-to-Speech-Content-Summarization-for-Indian-Languages
This project presents a multilingual pipeline for both speech-to-text and speech-to-speech...
EdVince/whisper-trtllm
Whisper in TensorRT-LLM
mahiiyh/asr-primer
A complete implementation of an Automatic Speech Recognition (ASR) system using OpenAI's Whisper...