synesthesiam
Follow
Lists (1)
Stars
Simple Speech-To-Text on the '10 cents' CH32V003 Microcontroller
Easily create text-to-speech models in any voice for rhasspy/piper. Make a text-to-speech model with your own voice recordings, or use thousands of RVC voices. Works offline on a Raspberry pi. Rapi…
Make Linux speak what's on the screen: clearly and securely.
Perl implementation of the Naval Research Laboratory text-to-phoneme algorithm, described by Elovitz et al (1976)
A Home Assistant integration & Model to control your smart home using a Local LLM
Wyoming protocol server for the Whisper API speech to text system
bookbot-hive / babygruut
Forked from rhasspy/gruutA tokenizer, text cleaner, and phonemizer for many human languages.
ESPHome definition for an AirGradient DIY device to send data to HomeAssistant and AirGradient servers
A TensorFlow based wake word detection training framework using synthetic sample generation suitable for certain microcontrollers.
Python class for converting numbers into Bulgarian cyrillic words
stb single-file public domain libraries for C/C++
AI powered speech denoising and enhancement
Accentor and transcriptor for Russian language
Detect wake words for ESPHome's voice assistant component on the device
Free speech dataset consisting of 24018 short audio clips of a single speaker reading sentences in Polish
LibrosaCpp is a c++ implemention of librosa to compute short-time fourier transform coefficients,mel spectrogram or mfcc
Manipulate audio with a simple and easy high level interface
Community Collection of Wake-Words for Home Assistant
A modified VITS that utilizes phoneme duration's ground truth for better robustness
Pytorch implementation of SELF-ATTENTIVE VAD, ICASSP 2021
state-of-the-art models for diacritics restoration for Arabic language
Using FastChat-T5 Large Language Model, Vosk API for automatic speech recognition, and Piper for text-to-speech
PyTorch code implementation of EfficientSpeech - to be presented at ICASSP2023.
Fast audio data augmentation in PyTorch. Inspired by audiomentations. Useful for deep learning.