Skip to content

Entry

SpeechBrain

Appears in 5 awesome lists

PyTorch speech toolkit with recipes for ASR, TTS, speaker recognition, and speech enhancement.

Open github.comspeechbrain/speechbrain

Found in these lists

Awesome Speaker Diarization

Section: Framework · SpeechBrain is an open-source and all-in-one speech toolkit based on PyTorch.

FreshScore 87

awesome-huggingface

Section: Speech · A PyTorch-based speech toolkit.

ArchivedScore 55

Awesome Open Source AI

Section: 2. Model Codebases & Model Families · PyTorch speech toolkit with recipes for ASR, TTS, speaker recognition, and speech enhancement.

FreshScore 87

awesome-python

Section: Other · A PyTorch-based Speech Toolkit

FreshScore 79

Awesome-Pytorch-list

Section: NLP & Speech Processing: · SpeechBrain is an open-source and all-in-one speech toolkit based on PyTorch.

FreshScore 73

Whisper

General-purpose speech recognition model for multilingual transcription, translation, language identification, and related speech tasks. Python · Self-host · infra.

In 13 listsDetails

FunASR

industrial-grade ASR toolkit; 170× realtime on GPU, 50+ languages, built-in VAD, punctuation, speaker diarization, and emotion detection. Includes non-autoregressive SenseVoice and LLM-based Fun-ASR-Nano models.

In 12 listsDetails

Kaldi

Kaldi is a toolkit for speech recognition written in C++ and licensed under the Apache License v2.0. Kaldi is intended for use by speech recognition researchers.

In 5 listsDetails

FluidAudio

SDK for real-time on-device audio intelligence on iOS/macOS (diarization, identification, VAD, separation, embeddings, ASR), with CoreML models converted directly from PyTorch to leverage Apple Neural Engine performance.

In 4 listsDetails

NeMo

NVIDIA NeMo is a scalable and cloud-native generative AI framework built for researchers and PyTorch developers working on Large Language Models (LLMs), Multimodal Models (MMs), Automatic Speech Recognition (ASR), Text to Speech (TTS), and Computer Vision (CV) domains. It is designed to help you…

In 4 listsDetails

ESPnet

ESPnet is an end-to-end speech processing toolkit for tasks like speech recognition, translation, and enhancement, using PyTorch and Kaldi-style data processing.

In 4 listsDetails

VibeVoice

VibeVoice is a novel framework designed for generating expressive, long-form, multi-speaker conversational audio, such as podcasts, from text. It addresses significant challenges in traditional Text-to-Speech (TTS) systems, particularly in scalability, speaker consistency, and natural turn-taking.

In 4 lists

VoxCPM

Open-sourced tokenizer-free multilingual speech synthesis model with high-quality TTS and style transfer workflows.

In 4 lists