Reverb

Open-source inference code for speech recognition and speaker segmentation models.

CommonProductProgrammingSpeech RecognitionSpeaker Segmentation

Reverb is an open-source inference codebase for speech recognition and speaker segmentation models, utilizing the WeNet framework for ASR and the Pyannote framework for speaker segmentation. It offers detailed model descriptions and allows users to download models from Hugging Face. Reverb aims to provide developers and researchers with high-quality tools for various speech processing tasks.

Speech recognition code based on the WeNet framework
Speaker segmentation code based on the Pyannote framework
Provides WER and WDER results for long-form speech recognition and speaker segmentation
Supports model downloads via Hugging Face Hub
Offers Docker images to simplify deployment
Compatible with NVIDIA GPUs for enhanced performance
Includes detailed installation and usage instructions

\The target audience primarily includes researchers
developers
and corporate users in the fields of speech recognition and speaker segmentation. Reverb provides high-quality speech processing tools suitable for tasks such as meeting transcription and phone call analysis.\

Automatic speech recognition and speaker segmentation for meeting documentation
Voice content analysis for customer service call recordings
Transcription and speaker identification for courtroom records

1. Ensure that Git Large File Storage (LFS) is installed on your system.
2. Use HUGGINGFACE_ACCESS_TOKEN to download models from the Hugging Face Hub.
3. Clone the Reverb code repository to your local machine.
4. Set up and activate a virtual environment.
5. At the root directory of the code repository

Visit

Reverb Visit Over Time

Monthly Visits

494758773

Bounce Rate

37.69%

Page per Visit

5.7

Visit Duration

00:06:29

Reverb Visit Trend

Reverb Visit Geography

Reverb Traffic Sources

Reverb Alternatives

OLMo 2 7B — A large language model with 7 billion parameters, enhancing natural language processing capabilities.

Programming•Large Language Model•Natural Language Processing

Skywork-o1-Open-PRM-Qwen-2.5-1.5B — Skywork o1 Open series models enhance the capability to solve complex problems.

Programming•AI Reasoning•Model

Transcribro — Private, on-device speech recognition keyboard and text service on the Android platform.

Productivity•Android•Speech Recognition

132

OmniSenseVoice — Ultra-fast speech recognition with precise timestamps

Productivity•Speech Recognition•Timestamping

486

Mini-Omni — An open-source multimodal large language model that supports real-time voice input and streaming audio output.

Productivity•Multimodal•Speech Recognition

456

OpenVoiceChat — Engage in natural voice conversations with large language models.

chatting•Speech Recognition•Text-to-Speech

282

speech-to-speech — Open-source speech-to-speech conversion module

Programming•Speech Recognition•Natural Language Processing

540

whisper-diarization — Automatic speech recognition and speaker segmentation based on OpenAI Whisper

Programming•Speech Recognition•Speaker Segmentation

240

WeST — Implement speech transcription based on LLM in just 300 lines of code.

Programming•Speech Recognition•Natural Language Processing

102

FunAudioLLM — Foundation model for natural voice interaction understanding and generation

Others•Speech Recognition•Speech Synthesis

552

RWKV-6 Finch 7B World 3 — An open-source AI model with 7 billion parameters and trained on 3.1 trillion tokens.

Programming•AI Model•Open Source

Q-RWKV-6 32B Instruct Preview — The most powerful variant of the RWKV model, breaking multiple English benchmark tests.

Programming•Machine Learning•Natural Language Processing

VideoSeal — An open and efficient video watermarking technology

Video•Video Watermarking•Copyright Protection

L1B3RT4S — Harmless AI liberation prompts provided for well-intentioned small AIs.

OpenSource•Liberation•Open Source

diagen — An intuitive reflection graph generated with one click.

Programming•Chart Generation•Data Visualization

Desk-Emoji — An open-source AI desktop robot featuring an expression screen, dual-axis console, and voice chat functionality.

Entertainment•Desktop Robot•Expression Screen

MCP Directory — MCP Server Directory, gathering multiple MCP server resources.

Programming•MCP•MCP Server

ComfyUI-MMAudio — ComfyUI node designed for audio processing using the MMAudio model.

Music•Audio Processing•MMAudio

mcp-cli — Command-line inspection tool for the Model Context Protocol

Programming•MCP•Command-line tools

InternVL2_5-26B — A large multimodal language model that integrates visual and linguistic understanding.

Image•Multimodal•Large Language Model

Sana_600M_1024px — High-resolution, efficient text-to-image generation framework

Image•Text-to-image•High resolution

Agentless — An agentless approach to automatically resolve software development issues

Programming•Automated Repair•Software Engineering

FineWeb2 — Multilingual Pretrained Dataset

Programming•Multilingual•Pretrained

ClearerVoice-Studio — An open-source AI voice processing toolkit supporting voice enhancement, separation, and target speaker extraction.

Productivity•Voice Processing•Open Source

252

Sana_1600M_1024px — A high-resolution, efficient text-to-image generation framework.

Image•Text-to-image•High resolution

Sana_1600M_512px — High-resolution and efficient text-to-image generation framework.

Image•Text-to-image•High resolution

Best AI Websites & Tools

Reverb

Reverb Visit Over Time

Reverb Visit Trend

Reverb Visit Geography

Reverb Traffic Sources

Reverb Alternatives

OLMo 2 7B — A large language model with 7 billion parameters, enhancing natural language processing capabilities.

Skywork-o1-Open-PRM-Qwen-2.5-1.5B — Skywork o1 Open series models enhance the capability to solve complex problems.

Transcribro — Private, on-device speech recognition keyboard and text service on the Android platform.

OmniSenseVoice — Ultra-fast speech recognition with precise timestamps

Mini-Omni — An open-source multimodal large language model that supports real-time voice input and streaming audio output.

OpenVoiceChat — Engage in natural voice conversations with large language models.

speech-to-speech — Open-source speech-to-speech conversion module

whisper-diarization — Automatic speech recognition and speaker segmentation based on OpenAI Whisper

WeST — Implement speech transcription based on LLM in just 300 lines of code.

FunAudioLLM — Foundation model for natural voice interaction understanding and generation

Unitree RL GYM — Unitree robot platform for reinforcement learning

Recursal AI — Making artificial intelligence accessible

OmniAudio-2.6B — The fastest edge-deployed audio language model in the world.

RWKV-6 Finch 7B World 3 — An open-source AI model with 7 billion parameters and trained on 3.1 trillion tokens.

Q-RWKV-6 32B Instruct Preview — The most powerful variant of the RWKV model, breaking multiple English benchmark tests.

VideoSeal — An open and efficient video watermarking technology

L1B3RT4S — Harmless AI liberation prompts provided for well-intentioned small AIs.

diagen — An intuitive reflection graph generated with one click.

Desk-Emoji — An open-source AI desktop robot featuring an expression screen, dual-axis console, and voice chat functionality.

MCP Directory — MCP Server Directory, gathering multiple MCP server resources.

ComfyUI-MMAudio — ComfyUI node designed for audio processing using the MMAudio model.

mcp-cli — Command-line inspection tool for the Model Context Protocol

InternVL2_5-26B — A large multimodal language model that integrates visual and linguistic understanding.

Sana_600M_1024px — High-resolution, efficient text-to-image generation framework

Agentless — An agentless approach to automatically resolve software development issues

FineWeb2 — Multilingual Pretrained Dataset

ClearerVoice-Studio — An open-source AI voice processing toolkit supporting voice enhancement, separation, and target speaker extraction.

Sana_1600M_1024px — A high-resolution, efficient text-to-image generation framework.

Sana_1600M_512px — High-resolution and efficient text-to-image generation framework.