Open-Speech-EkStep/vakyansh-wav2vec2-experimentation
Repository containing experimentation platform on how to train, infer on wav2vec2 models.
Supports complete wav2vec2 lifecycle workflows across pretraining, finetuning, and inference with YAML-based configuration management, integrating KenLM for language model decoding and Flashlight for CTC criterion. Includes data preparation pipelines with automatic WER evaluation, manifest generation, and support for Indic language models stored in a separate model repository.
No commits in the last 6 months.
Stars
88
Forks
40
Language
Python
License
MIT
Category
Last pushed
Sep 22, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/Open-Speech-EkStep/vakyansh-wav2vec2-experimentation"
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.
silversparro/wav2letter.pytorch
A fully convolution-network for speech-to-text, built on pytorch.