inboxpraveen/Speech-Annotation-Tool
Review, correct, and export ASR transcripts at scale. Web-based ASR accuracy workbench for reviewing, correcting, and exporting speech-to-text transcripts using Whisper, FFmpeg, and Flask.
This tool helps data annotation teams and researchers efficiently review, correct, and export speech-to-text transcripts. You can either upload audio files to automatically transcribe them using AI, or load existing audio chunks with their current Excel transcripts for manual editing. The result is a refined and accurate dataset of audio transcripts, ready for use in various applications.
Use this if you need a streamlined way to improve the accuracy of automatically generated speech transcripts, especially for large volumes of audio.
Not ideal if you're looking for a fully automated, hands-off transcription solution without any human review or correction component.
Stars
10
Forks
2
Language
Python
License
MIT
Category
Last pushed
Dec 24, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/inboxpraveen/Speech-Annotation-Tool"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
linto-ai/whisper-timestamped
Multilingual Automatic Speech Recognition with word-level timestamps and confidence
argmaxinc/WhisperKit
On-device Speech Recognition for Apple Silicon
yeyupiaoling/Whisper-Finetune
Fine-tune the Whisper speech recognition model to support training without timestamp data,...
vasistalodagala/whisper-finetune
Fine-tune and evaluate Whisper models for Automatic Speech Recognition (ASR) on custom datasets...
xenova/whisper-web
ML-powered speech recognition directly in your browser