sciforce/phones-las
Articulatory features estimation using Listen Attend and Spell architecture.
This project helps linguists and speech scientists analyze spoken language by taking audio recordings and identifying either the phonetic sounds (phones), words, characters, or the underlying articulatory features (like tongue position) within them. It produces a detailed transcription or a breakdown of these features. Researchers in phonetics, speech pathology, or linguistics who need to systematically study the building blocks of speech would use this.
No commits in the last 6 months.
Use this if you need to accurately detect and transcribe phonetic sounds or articulatory features from audio speech datasets for linguistic research or speech analysis.
Not ideal if you're looking for a simple, off-the-shelf voice-to-text solution for general transcription or virtual assistants, as it requires technical setup and data preparation.
Stars
33
Forks
6
Language
Python
License
Apache-2.0
Category
Last pushed
Apr 24, 2020
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/sciforce/phones-las"
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)