daanzu/deepspeech-websocket-server
Server & client for DeepSpeech using WebSockets for real-time speech recognition in separate environments
Implements streaming inference via Mozilla's DeepSpeech with voice activity detection (VAD) on the client to segment utterances and filter noise. The server handles multi-user connections using gevent WebSockets with sequential decoding, while the client streams raw audio from PyAudio-compatible microphone interfaces. Supports DeepSpeech v0.2+ with configurable CTC decoder parameters (language model weight, beam width, vocabulary insertion penalty) and optional utterance saving for model validation.
103 stars. No commits in the last 6 months.
Stars
103
Forks
31
Language
Python
License
MPL-2.0
Category
Last pushed
May 29, 2020
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/daanzu/deepspeech-websocket-server"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
shibing624/parrots
Automatic Speech Recognition(ASR), Text-To-Speech(TTS) engine. 中英语音识别、多角色语音合成，支持多语言，准确率高
MainRo/deepspeech-server
A testing server for a speech to text service based on coqui.ai
altunenes/parakeet-rs
very fast speech-to-text, diarization, streaming (even in CPU) with NVIDIA Parakeet in Rust
thewh1teagle/pyannote-rs
pyannote audio diarization in rust
PaddlePaddle/Parakeet
PAddle PARAllel text-to-speech toolKIT (supporting Tacotron2, Transformer TTS,...