msalhab96/Conformer
An implementation for "Conformer: Convolution-augmented Transformer for Speech Recognition" Paper
This project helps speech engineers convert spoken audio into written text. You provide audio files and their corresponding transcripts, and it trains a specialized model that can accurately transcribe new speech. It's designed for researchers or practitioners building custom speech-to-text systems.
No commits in the last 6 months.
Use this if you need to train a high-performance, custom speech recognition model from scratch using your own audio and transcription data.
Not ideal if you're looking for an off-the-shelf transcription service or a tool that doesn't require setting up a development environment and managing model training.
Stars
20
Forks
1
Language
Python
License
MIT
Category
Last pushed
Aug 16, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/msalhab96/Conformer"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
khanld/chunkformer
ChunkFormer: Masked Chunking Conformer For Long-Form Speech Transcription
sooftware/conformer
[Unofficial] PyTorch implementation of "Conformer: Convolution-augmented Transformer for Speech...
upskyy/Squeezeformer
PyTorch implementation of "Squeezeformer: An Efficient Transformer for Automatic Speech...
WindQAQ/listen-attend-and-spell
Tensorflow implementation of "Listen, Attend and Spell" authored by William Chan. This project...
jackaduma/LAS_Mandarin_PyTorch
Listen, attend and spell Model and a Chinese Mandarin Pretrained model (中文-普通话 ASR模型)