mailong25/self-supervised-speech-recognition
speech to text with self-supervised learning based on wav2vec 2.0 framework
This helps speech recognition practitioners develop highly accurate speech-to-text models for any language, even with limited transcribed audio. You provide audio files (both labeled with transcripts and unlabeled) and text data, and it outputs a custom speech recognition model. This is for data scientists, linguists, or AI engineers who need to build robust transcription systems for specific languages or domains.
379 stars. No commits in the last 6 months.
Use this if you need to create a custom speech-to-text model for a specific language or accent and have access to some audio data and text, but not necessarily massive amounts of transcribed audio.
Not ideal if you're looking for an out-of-the-box, plug-and-play solution without needing to collect or process your own datasets and train models.
Stars
379
Forks
116
Language
Python
License
—
Category
Last pushed
Nov 22, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/mailong25/self-supervised-speech-recognition"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
liangstein/Chinese-speech-to-text
Chinese Speech To Text Using Wavenet
louiskirsch/speechT
An opensource speech-to-text software written in tensorflow
Open-Speech-EkStep/vakyansh-models
Open source speech to text models for Indic Languages
oliverguhr/wav2vec2-live
A live speech recognition using Facebooks wav2vec 2.0 model.
Open-Speech-EkStep/vakyansh-wav2vec2-experimentation
Repository containing experimentation platform on how to train, infer on wav2vec2 models.