STT - a Drishti Collection

Drishti 's Collections

vlm-unlearning-benchmarks

LLMs

music generation

biomed ner models + spaces

medllms

STT

Podcast

Summarizer (Mono + Multi-lingual)

Personal Stylist + Ecom Assistant

Elsa

Professional Development

Research Co-pilot

GitHub

Search and Monitor Gradio MCP Server + REST API

Environment/Climate/Agriculture

OCR

MCP Router + Customizable MCP Agents

Imp Leaderboards

medical/clinical/health

web search + scrape

TTS

One-stop Knowledge Solution

Intellectual Property One-Stop Solution

VLMs

STT

updated Jun 25

Running on Zero

990

Whisper Turbo

🤯

990

Transcribe audio or YouTube videos into text
Build error

Deepspeech_live_speech_to_text

🏃
facebook/wav2vec2-base-960h

Automatic Speech Recognition • 94.4M • Updated Nov 14, 2022 • 2.39M • 383
kyutai/stt-1b-en_fr

Automatic Speech Recognition • Updated 13 days ago • 98

Note kyutai released new speech-to-text models that come in 1B & 2B