Statistics for topic speech

A fast multimodal LLM for real-time voice

🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production

WhisperX: Automatic Speech Recognition with Word-level Timestamps (& Diarization)

Grounded SAM: Marrying Grounding DINO with Segment Anything & Stable Diffusion & Recognize Anything - Automatically Detect , Segment and Generate Anything

SoftVC VITS Singing Voice Conversion

A fast multimodal LLM for real-time voice

A Survey of Spoken Dialogue Models (60 pages)

Text-to-speech API endpoint compatible with OpenAI's TTS API endpoint, using Microsoft Edge TTS to generate speech for free locally

This repository contains the training, inference, evaluation code for SpeechLLM models and details about the model releases on huggingface.

An Open-Sourced LLM-empowered Foundation TTS System

A Survey of Spoken Dialogue Models (60 pages)

A fast multimodal LLM for real-time voice

🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production

WhisperX: Automatic Speech Recognition with Word-level Timestamps (& Diarization)

A Survey of Spoken Dialogue Models (60 pages)

SoftVC VITS Singing Voice Conversion

A Survey of Spoken Dialogue Models (60 pages)

A fast multimodal LLM for real-time voice

Text-to-speech API endpoint compatible with OpenAI's TTS API endpoint, using Microsoft Edge TTS to generate speech for free locally

Dataset of ICASSP 2021 MULTILINGUAL PHONETIC DATASET FOR LOW RESOURCE SPEECH RECOGNITION

Verbatim Automatic Speech Recognition with improved word-level timestamps and filler detection

A Survey of Spoken Dialogue Models (60 pages)

🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production

WhisperX: Automatic Speech Recognition with Word-level Timestamps (& Diarization)

Speech To Speech: an effort for an open-sourced and modular GPT4-o

A fast multimodal LLM for real-time voice

SoftVC VITS Singing Voice Conversion

A Survey of Spoken Dialogue Models (60 pages)

Text-to-speech API endpoint compatible with OpenAI's TTS API endpoint, using Microsoft Edge TTS to generate speech for free locally

An Open-Sourced LLM-empowered Foundation TTS System

A fast multimodal LLM for real-time voice

This repository contains the training, inference, evaluation code for SpeechLLM models and details about the model releases on huggingface.

Foundational model for human-like, expressive TTS

Speech To Speech: an effort for an open-sourced and modular GPT4-o

MARS5 speech model (TTS) from CAMB.AI

Voice Recognition to Text Tool / 一个离线运行的本地音视频转字幕工具，输出json、srt字幕、纯文字格式

A fast multimodal LLM for real-time voice

🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production

WhisperX: Automatic Speech Recognition with Word-level Timestamps (& Diarization)

SoftVC VITS Singing Voice Conversion

Foundational model for human-like, expressive TTS

Grounded SAM: Marrying Grounding DINO with Segment Anything & Stable Diffusion & Recognize Anything - Automatically Detect , Segment and Generate Anything

Voice Recognition to Text Tool / 一个离线运行的本地音视频转字幕工具，输出json、srt字幕、纯文字格式

StreamSpeech is an “All in One” seamless model for offline and simultaneous speech recognition, speech translation and speech synthesis.

MARS5 speech model (TTS) from CAMB.AI

Foundational model for human-like, expressive TTS

A ggml (C++) re-implementation of tortoise-tts