liangstein/Chinese-speech-to-text
Chinese Speech To Text Using Wavenet
Implements WaveNet architecture for character-level Chinese speech recognition trained on the THCHS30 dataset, eliminating the need for word vectorization by operating directly on phonetic units. Built with Keras/TensorFlow backend and achieves 0.2768 CTC loss on 10,000 training samples, though performance degrades significantly in noisy conditions and would benefit from larger, more diverse datasets.
163 stars. No commits in the last 6 months.
Stars
163
Forks
55
Language
Python
License
Apache-2.0
Category
Last pushed
May 03, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/liangstein/Chinese-speech-to-text"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
louiskirsch/speechT
An opensource speech-to-text software written in tensorflow
Open-Speech-EkStep/vakyansh-models
Open source speech to text models for Indic Languages
Open-Speech-EkStep/vakyansh-wav2vec2-experimentation
Repository containing experimentation platform on how to train, infer on wav2vec2 models.
oliverguhr/wav2vec2-live
A live speech recognition using Facebooks wav2vec 2.0 model.
silversparro/wav2letter.pytorch
A fully convolution-network for speech-to-text, built on pytorch.