Rishit-dagli/Conformer

An implementation of Conformer: Convolution-augmented Transformer for Speech Recognition, a Transformer Variant in TensorFlow/Keras

42
/ 100
Emerging

This project provides an implementation of Conformer, a state-of-the-art neural network architecture designed for speech recognition. It takes raw audio sequences as input and processes them to improve the accuracy of speech-to-text conversion. This is ideal for machine learning engineers and researchers working on building or improving automated speech recognition (ASR) systems.

No commits in the last 6 months.

Use this if you are a machine learning engineer or researcher developing advanced speech recognition models and need a robust, high-performance building block in TensorFlow/Keras.

Not ideal if you are looking for a pre-trained, ready-to-use speech-to-text API or a tool for general audio processing tasks.

speech-recognition audio-processing machine-learning-engineering deep-learning-research natural-language-processing
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 18 / 25

How are scores calculated?

Stars

45

Forks

12

Language

Python

License

Apache-2.0

Last pushed

Jan 20, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/Rishit-dagli/Conformer"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.