BRSpeech: A Portuguese Dataset for Speech Synthesis

A implementation of Power Normalized Cepstral Coefficients: PNCC

Web app, command-line interface and Python library for synthesizing Chinese texts into speech.

Automatically setup the AISHELL-4 and MSDWild dataset for usage with pyannote-database (and pyannote-audio)

Code for the paper "Toward Fully Self-Supervised Multi-Pitch Estimation".

A high-throughput and memory-efficient inference and serving engine for Whisper, https://mesolitica.com/blog/vllm-whisper

[IEEE/ACM-TASLP 2024] Controllable Accented Text-to-Speech Synthesis with Fine and Coarse-Grained Intensity Rendering

[Neural Networks'2021] FastTalker: A neural text-to-speech architecture with shallow and group autoregression

[ICASSP'2020] Teacher-Student Training for Robust Tacotron-based TTS

Lightweight wrapper for Silero VAD using internal ONNX Runtime and with no python package dependencies

Diffusion-based singing voice pitch correction

A simple FastAPI Server to run XTTSv2

The Official Code Repo of SafeEar (Accepted by CCS 2024)

PyTorch implementation of WaveFit [2022, Google] which is one of SOTA lightweight/fast speech vocoders.

Stutter-Solver: End-to-end Cross-lingual Dysfluency Detection

StreamHiFiGAN offers a HiFiGAN vocoder model optimized for streaming inference, providing real-time audio synthesis capabilities.

Using Pre-trained SSL Transformer Models for Speaker Verification

The source code for the Interspeech 2024 paper "Lightweight Transducer Based on Frame Level Criterion".

Elementary is a JavaScript library for digital audio signal processing.

SAMO: SPEAKER ATTRACTOR MULTI-CENTER ONE-CLASS LEARNING FOR VOICE ANTI-SPOOFING

This is a general framework for fake audio detection using pytorch lightning

MTDA-HSED: Mutual-Assistance Tuning and Dual-Branch Aggregating for Heterogeneous Sound Event Detection