Berkeley-Speech-Group/sylber
Sylber: Syllabic Embedding Representation of Speech from Raw Audio
Sylber helps speech scientists and researchers break down raw audio recordings into very short, meaningful units based on syllables. You provide an audio file, and it outputs precise start and end times for each syllable, along with numerical representations of those syllable segments. This tool is designed for anyone working with spoken language who needs a granular analysis of speech.
No commits in the last 6 months. Available on PyPI.
Use this if you need to analyze speech at the sub-word, syllabic level to understand pronunciation patterns, language development, or vocal characteristics.
Not ideal if you're looking for full-sentence transcription or speaker identification; this focuses on the fine-grained segmentation of individual syllables.
Stars
74
Forks
6
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Mar 17, 2025
Commits (30d)
0
Dependencies
15
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/Berkeley-Speech-Group/sylber"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
espnet/espnet
End-to-End Speech Processing Toolkit
yeyupiaoling/PPASR
基于PaddlePaddle实现端到端中文语音识别，从入门到实战，超简单的入门案例，超实用的企业项目。支持当前最流行的DeepSpeech2、Conformer、Squeezeformer模型
yeyupiaoling/PaddlePaddle-DeepSpeech
基于PaddlePaddle实现的语音识别，中文语音识别。项目完善，识别效果好。支持Windows，Linux下训练和预测，支持Nvidia Jetson开发板预测。
flashlight/wav2letter
Facebook AI Research's Automatic Speech Recognition Toolkit
pannous/tensorflow-speech-recognition
🎙Speech recognition using the tensorflow deep learning framework, sequence-to-sequence neural networks