kurianbenoy/malayalam_asr_benchmarking
A study to benchmark whisper based ASRs in Malayalam
This project helps developers and researchers evaluate the accuracy of speech-to-text models for the Malayalam language. By inputting specific Whisper or faster-Whisper based ASR models and a Malayalam speech dataset, it produces Word Error Rate (WER) and Character Error Rate (CER) metrics. This is useful for AI/ML engineers or computational linguists working on speech technology.
No commits in the last 6 months. Available on PyPI.
Use this if you are developing or selecting an Automatic Speech Recognition (ASR) model for Malayalam and need to compare different Whisper-based options rigorously.
Not ideal if you are a non-technical end-user simply looking to transcribe Malayalam speech without needing to evaluate model performance.
Stars
11
Forks
1
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Apr 15, 2024
Commits (30d)
0
Dependencies
10
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/kurianbenoy/malayalam_asr_benchmarking"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Featured in
Higher-rated alternatives
Uberi/speech_recognition
Speech recognition module for Python, supporting several engines and APIs, online and offline.
cmusphinx/pocketsphinx
A small speech recognizer
tensorflow/lingvo
Lingvo
modelscope/FunASR
A Fundamental End-to-End Speech Recognition Toolkit and Open Source SOTA Pretrained Models,...
PyThaiNLP/pythaiasr
Python Thai Automatic Speech Recognition