SakshiRathi77/hindiSpeechPro-Automatic-Speech-Recognization

The project,being part of Kagglex BIPOC Mentorship Program final project, aims to train two separate Hindi ASR models using the Facebook Wav2Vec2 (300M parameters) and OpenAI Whisper-Small models, respectively. The goal is to compare their performance, with a target WER of less than 13%, across various Hindi accents and dialects.

27
/ 100
Experimental

This project helps convert spoken Hindi audio into written text accurately, accounting for various accents and dialects. You provide audio recordings in Hindi, and it produces a textual transcription. This is ideal for anyone working with Hindi audio content, such as content creators, linguists, or customer service analysts.

No commits in the last 6 months.

Use this if you need to reliably transcribe Hindi speech into text, especially across different accents and dialects, and want to understand the performance differences between leading speech recognition technologies.

Not ideal if you primarily need speech recognition for languages other than Hindi, or if your application requires extremely low latency real-time transcription where computational efficiency is the absolute top priority without comparison needs.

Hindi language processing speech-to-text audio transcription linguistic analysis content localization
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 8 / 25
Community 14 / 25

How are scores calculated?

Stars

11

Forks

3

Language

Jupyter Notebook

License

Last pushed

Nov 13, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/SakshiRathi77/hindiSpeechPro-Automatic-Speech-Recognization"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.