Automated Multi Speaker diarization API for meetings, calls, interviews, press-conference etc.

This repository consists of unsupervised segmentation of audio files consist of music and speech.

Fork of the repository by taylorlu, modified for usability and without changing the pretrained models

Neural network based similarity scoring for diarization (pytorch implementation of "LSTM based Similarity Measurement with Spectral Clustering for Speaker Diarization")

Resources for easily building ASR systems with Kaldi

Large publicly available speech datasets

Kit de desenvolvimento de aplicações em Python para o CPQD Transcrição de Diálogos

无监督说话人聚类算法比较

Speech toolkit for audio analysis, diarization and transcription

Research on speech processing, speaker identification and audio diarization

Convert kaldi feature extraction and nnet3 models into Tensorflow Lite models. Currently aimed at converting kaldi's x-vector models and diarization pipelines to tensorflow models.

Easy to use Multi-Provider ASR/Speech To Text and NLP engine

Speech Detection and Diarization

Ara (think parrot 🦜 ) is a script / api to transcribe and diarise audio. It uses Whisper and Pyannote

Identify the emotion of multiple speakers in an Audio Segment

Transcribe real-world speech with an API call. Based on Whisper(ASR by OpenAI) - https://openai.com/blog/whisper/

Gecko - A Tool for Effective Annotation of Human Conversations

Speaker Diarization using Python, Flask and Html

A simple Python package for analyzing the necessary data in Speaker Diarization using oracle RTTM files and audio files.