daveshap/keras_asr
ASR experiment using Google's Universal Sentence Encoder
This helps researchers and developers who are exploring new ways to convert spoken language into written text, particularly in experimental setups. It takes raw audio and its corresponding human-written transcriptions to create a system that can then transform new audio recordings into encoded representations and finally into text. This is designed for those working on advanced speech-to-text methodologies.
No commits in the last 6 months.
Use this if you are a researcher or AI/ML engineer experimenting with novel audio processing and natural language encoding techniques for speech recognition.
Not ideal if you need a ready-to-use, high-performance speech-to-text system for production applications without deep customization.
Stars
9
Forks
2
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Sep 26, 2018
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/daveshap/keras_asr"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
TensorSpeech/TensorFlowASR
:zap: TensorFlowASR: Almost State-of-the-art Automatic Speech Recognition in Tensorflow 2....
dangvansam/viet-asr
VietASR - Vietnamese Automatic Speech Recognition
wenet-e2e/wenet
Production First and Production Ready End-to-End Speech Recognition Toolkit
xinjli/allosaurus
Allosaurus is a pretrained universal phone recognizer for more than 2000 languages
srvk/eesen
The official repository of the Eesen project