speech-processing
maths-cs-ai-compendium
Become a cracked AI/ML researcher/engineer with this unconventional textbook covering maths, computing, and ML with intuition.
- 7.7k
- TypeScript
- Apache-2.0
- 4 mo ago
whisper-timestamped
Multilingual Automatic Speech Recognition with word-level timestamps and confidence
- 2.9k
- Python
- AGPL-3.0
- 7 wk ago
deepvoice3_pytorch
PyTorch implementation of convolutional neural networks-based text-to-speech synthesis models
- 2k
- Python
- 3 y ago
awesome-diarization
A curated list of awesome Speaker Diarization papers, libraries, datasets, and other resources.
- 1.9k
- Apache-2.0
- 3 wk ago
StreamSpeech
StreamSpeech is an βAll in Oneβ seamless model for offline and simultaneous speech recognition, speech translation and speech synthesis.
- 1.3k
- Python
- MIT
- 17 mo ago
open-speech-corpora
π A list of accessible speech corpora for ASR, TTS, and other Speech Technologies
- 1.4k
- MIT
- 2 y ago
CrisperWhisper
Controllable Transcription. Verbatim ( every, filler, pause, stutter, vocal sound) , or intended ( what the speaker meant to say, optimized for readability) with word-level timestamps.
- 1.5k
- Python
- 8 d ago
MultiBench
[NeurIPS 2021] Multiscale Benchmarks for Multimodal Representation Learning
- 657
- HTML
- MIT
- 3 y ago
Tutorial_Separation
This repo summarizes the tutorials, datasets, papers, codes and tools for speech separation and speaker extraction task. You are kindly invited to pull requests.
- 489
- MATLAB
- 6 y ago
audio-development-tools
Audio Development Tools (ADT) is a project for advancing sound, speech, and music technologies, featuring components for machine learning, sound synthesis, speech and music generation, signal processing, game audio, digital audio workstations (DAWs), and more.
- 475
- MIT
- 17 mo ago
speechbrain.github.io
The SpeechBrain project aims to build a novel speech toolkit fully based on PyTorch. With SpeechBrain users can easily create speech processing systems, ranging from speech recognition (both HMM/DNN and end-to-end), speaker recognition, speech enhancement, speech separation, multi-microphone speech processing, and many others.
- 374
- HTML
- 17 mo ago
NonAutoregGenProgress
Tracking the progress in non-autoregressive generation (translation, transcription, etc.)
- 298
- CC0-1.0
- 4 y ago
NLP-Guide
Natural Language Processing (NLP). Covering topics such as Tokenization, Part Of Speech tagging (POS), Machine translation, Named Entity Recognition (NER), Classification, and Sentiment analysis.
- 121
- Python
- 3 y ago
SpeechGen
γSpeechGen: Unlocking the Generative Power of Speech Language Models with Promptsγ
- 77
- 3 y ago
wyoming-voice-match
A Wyoming protocol ASR proxy that verifies speaker identity and isolates voice commands from background noise before forwarding audio to a downstream speech-to-text service. Designed for Home Assistant voice pipelines to prevent false activations from TVs, radios, and other people - and to deliver clean transcripts even in noisy environments.
- 95
- Python
- MIT
- 4 mo ago
Tutorial_Speech_Signal_Processing
This repo summarizes the courses and materials for speech signal processing. You are kindly invited to pull requests.
- 104
- 6 y ago
human-voice-detection
Binary classification problem that aims to classify human voices from audio recordings. Implemented using PyTorch and Librosa.
- 36
- Python
- 5 y ago
SpEx
Implementation of "SpEx: Multi-Scale Time Domain Speaker Extraction Network".
- 37
- Python
- CC0-1.0
- 6 y ago
StreamUni
StreamUni is a framework that efficiently enables unified Large Speech-Language Models to accomplish streaming speech translation in a cohesive manner.
- 27
- Python
- 16 mo ago
FastLongSpeech
FastLongSpeech is a novel framework designed to extend the capabilities of Large Speech-Language Models for efficient long-speech processing without necessitating dedicated long-speech training data.
- 16
- Python
- 16 mo ago
voxrt-silero-android
On device streaming voice activity detection (Silero VAD v5) for Android. ~424 KB native binary, NEON-accelerated arm64-v8a, RTF ~3% on Snapdragon 662.
- 17
- Kotlin
- Apache-2.0
- 2 mo ago
voxrt-silero-ios
On device streaming voice activity detection (Silero VAD v5) for iOS. Custom Rust inference runtime, NEON-accelerated arm64, RTF ~1.85% on iPhone.
- 14
- Swift
- Apache-2.0
- 2 mo ago
voxrt-wake-word-android
Always-on wake-phrase detection for Android on the VoxRT custom on-device inference runtime β Kotlin library, 16 kHz mono PCM in, threshold-crossing events out. Custom phrases at voxrt.com.
- 13
- Kotlin
- Apache-2.0
- 2 mo ago
voxrt-wake-word-ios
Always-on wake-phrase detection for iOS on the VoxRT custom on-device inference runtime β Swift Package, 16 kHz mono PCM in, threshold-crossing events out. Custom phrases at voxrt.com.
- 12
- Swift
- Apache-2.0
- 2 mo ago
awesome-self-supervised-speech-representation-learning
A comprehensive list of awesome self-supervised speech representation learning papers.
- 12
- 5 y ago
voxrt-wake-word-browser
On-device wake-phrase detection in the browser β WebAssembly + SIMD128, ~275 KB total (runtime + model), no server. Same runtime as voxrt-wake-word-{android,ios,linux}. Free demo tier of the VoxRT wake-word family.
- 11
- JavaScript
- Apache-2.0
- 2 mo ago
voxrt-kws-browser
On-device 14-way keyword spotting in the browser β WebAssembly + SIMD128, ~1.5 MB total (runtime + model), no server. Same runtime as voxrt-kws-{linux,android,ios}.
- 11
- JavaScript
- Apache-2.0
- 2 mo ago
voxrt-wake-word-models
Wake-phrase model weights (.vxrt, ~100 KB, AES-GCM encrypted) for the VoxRT custom on-device inference runtime. Paired with voxrt-wake-word-{android,ios,linux}. Custom phrases at voxrt.com.
- 11
- 2 mo ago












