sooftware/speech-transformer
Transformer implementation speciaized in speech recognition tasks using Pytorch.
This project offers a foundational building block for creating sophisticated speech recognition systems. It takes raw audio data, typically represented as feature vectors, and transforms it into predicted sequences of spoken words or phonemes. It's intended for machine learning engineers and researchers who are developing custom speech-to-text applications.
No commits in the last 6 months.
Use this if you are a machine learning engineer or researcher building a custom speech recognition model and need a robust Transformer architecture designed for audio processing.
Not ideal if you need a ready-to-use speech-to-text application or a full training pipeline, as this provides only the model architecture.
Stars
65
Forks
11
Language
Python
License
MIT
Category
Last pushed
Nov 28, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/sooftware/speech-transformer"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
TensorSpeech/TensorFlowASR
:zap: TensorFlowASR: Almost State-of-the-art Automatic Speech Recognition in Tensorflow 2....
dangvansam/viet-asr
VietASR - Vietnamese Automatic Speech Recognition
wenet-e2e/wenet
Production First and Production Ready End-to-End Speech Recognition Toolkit
xinjli/allosaurus
Allosaurus is a pretrained universal phone recognizer for more than 2000 languages
srvk/eesen
The official repository of the Eesen project