microsoft/UniSpeech
UniSpeech - Large Scale Self-Supervised Learning for Speech
This project provides pre-trained models that help extract meaningful information from spoken audio. You input raw speech recordings, and the models produce insights related to the content spoken or the speaker's identity. Researchers and developers working on speech-enabled applications or analytics would use these models.
479 stars. No commits in the last 6 months.
Use this if you need to build advanced speech recognition or speaker identification systems with high accuracy, leveraging models pre-trained on vast amounts of speech data.
Not ideal if you need a ready-to-use application for transcribing audio or identifying speakers without any development effort.
Stars
479
Forks
76
Language
Python
License
—
Category
Last pushed
Apr 05, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/microsoft/UniSpeech"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
Spr-Aachen/Easy-Voice-Toolkit
A user-friendly audio toolkit for voice recognition, voice transcription, voice conversion etc.
PrzemyslawSwiderski/python-gradle-plugin
Gradle plugin to run Python projects.
alphacep/awesome-russian-speech
Russian speech technology links
ftyers/commonvoice-utils
Linguistic processing for Common Voice
microsoft/SpeechT5
Unified-Modal Speech-Text Pre-Training for Spoken Language Processing