jiwidi/las-pytorch
Listen, Attend and spell model for E2E ASR. Implementation in Pytorch
This project offers a foundational implementation for converting spoken language into written text using deep learning. It takes raw audio files as input and outputs a sequence of predicted letters, aiming to transcribe speech accurately. Researchers and engineers working on speech-to-text systems or exploring deep learning architectures for audio processing would find this useful for experimentation and model development.
No commits in the last 6 months.
Use this if you are a researcher or engineer looking for a Pytorch implementation of the Listen, Attend and Spell model for Automatic Speech Recognition (ASR) to experiment with or build upon.
Not ideal if you need a production-ready, highly accurate speech-to-text solution out-of-the-box for immediate use.
Stars
42
Forks
4
Language
Python
License
—
Category
Last pushed
Jun 22, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/jiwidi/las-pytorch"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Compare
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)