Trending repositories for topic asr
A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)
WhisperX: Automatic Speech Recognition with Word-level Timestamps (& Diarization)
Speech-to-text, text-to-speech, speaker diarization, speech enhancement, and VAD using next-gen Kaldi with onnxruntime without Internet connection. Support embedded systems, Android, iOS, HarmonyOS, R...
Offline speech recognition API for Android, iOS, Raspberry Pi and servers with Python, Java, C# and Node
Automatic Speech Recognition with Speaker Diarization based on OpenAI Whisper
The media player for language learning, with dual subtitles, AI-generated subtitles, real-time translation, and more!
Easy-to-use Speech Toolkit including Self-Supervised Learning model, SOTA/Streaming ASR with punctuation, Streaming TTS with text frontend, Speaker Verification System, End-to-End Speech Translation a...
Open-source industrial-grade ASR models supporting Mandarin, Chinese dialects and English, achieving a new SOTA on public Mandarin ASR benchmarks, while also offering outstanding singing lyrics recogn...
Whisper & Faster-Whisper standalone executables for those who don't want to bother with Python.
This is a python API which allows you to get the transcript/subtitles for a given YouTube video. It also works for automatically generated subtitles and it does not require an API key nor a headless b...
实时语音交互数字人，支持端到端语音方案（GLM-4-Voice - THG）和级联方案（ASR-LLM-TTS-THG）。可自定义形象与音色，无须训练，支持音色克隆，首包延迟低至3s。Real-time voice interactive digital human, supporting end-to-end voice solutions (GLM-4-Voice - THG) and cas...
百聆 是一个类似GPT-4o的语音对话机器人，通过ASR+LLM+TTS实现，集成DeepSeek R1等优秀大模型，时延低至800ms，Mac等低配置也可运行，支持打断
Analyze videos using LLMs, Computer Vision and Automatic Speech Recognition
Verbatim Automatic Speech Recognition with improved word-level timestamps and filler detection
Multilingual Automatic Speech Recognition with word-level timestamps and confidence
OpenAI-Compatible Proxy Middleware for the Wyoming Protocol
Open-source industrial-grade ASR models supporting Mandarin, Chinese dialects and English, achieving a new SOTA on public Mandarin ASR benchmarks, while also offering outstanding singing lyrics recogn...
Dockerfile for WhisperX: Automatic Speech Recognition with Word-Level Timestamps and Speaker Diarization (Dockerfile, CI image build and test)
Speech-to-text, text-to-speech, speaker diarization, speech enhancement, and VAD using next-gen Kaldi with onnxruntime without Internet connection. Support embedded systems, Android, iOS, HarmonyOS, R...
实时语音交互数字人，支持端到端语音方案（GLM-4-Voice - THG）和级联方案（ASR-LLM-TTS-THG）。可自定义形象与音色，无须训练，支持音色克隆，首包延迟低至3s。Real-time voice interactive digital human, supporting end-to-end voice solutions (GLM-4-Voice - THG) and cas...
A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)
The media player for language learning, with dual subtitles, AI-generated subtitles, real-time translation, and more!
Analyze videos using LLMs, Computer Vision and Automatic Speech Recognition
Verbatim Automatic Speech Recognition with improved word-level timestamps and filler detection
百聆 是一个类似GPT-4o的语音对话机器人，通过ASR+LLM+TTS实现，集成DeepSeek R1等优秀大模型，时延低至800ms，Mac等低配置也可运行，支持打断
Whisper & Faster-Whisper standalone executables for those who don't want to bother with Python.
WhisperX: Automatic Speech Recognition with Word-level Timestamps (& Diarization)
Offline Speech Recognition with OpenAI Whisper and TensorFlow Lite for Android
Automatic Speech Recognition with Speaker Diarization based on OpenAI Whisper
Running speech to text model (whisper.cpp) in Unity3d on your local machine.
A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)
WhisperX: Automatic Speech Recognition with Word-level Timestamps (& Diarization)
Speech-to-text, text-to-speech, speaker diarization, speech enhancement, and VAD using next-gen Kaldi with onnxruntime without Internet connection. Support embedded systems, Android, iOS, HarmonyOS, R...
Offline speech recognition API for Android, iOS, Raspberry Pi and servers with Python, Java, C# and Node
Automatic Speech Recognition with Speaker Diarization based on OpenAI Whisper
Whisper & Faster-Whisper standalone executables for those who don't want to bother with Python.
The media player for language learning, with dual subtitles, AI-generated subtitles, real-time translation, and more!
Easy-to-use Speech Toolkit including Self-Supervised Learning model, SOTA/Streaming ASR with punctuation, Streaming TTS with text frontend, Speaker Verification System, End-to-End Speech Translation a...
百聆 是一个类似GPT-4o的语音对话机器人，通过ASR+LLM+TTS实现，集成DeepSeek R1等优秀大模型，时延低至800ms，Mac等低配置也可运行，支持打断
This is a python API which allows you to get the transcript/subtitles for a given YouTube video. It also works for automatically generated subtitles and it does not require an API key nor a headless b...
Open-source industrial-grade ASR models supporting Mandarin, Chinese dialects and English, achieving a new SOTA on public Mandarin ASR benchmarks, while also offering outstanding singing lyrics recogn...
Analyze videos using LLMs, Computer Vision and Automatic Speech Recognition
实时语音交互数字人，支持端到端语音方案（GLM-4-Voice - THG）和级联方案（ASR-LLM-TTS-THG）。可自定义形象与音色，无须训练，支持音色克隆，首包延迟低至3s。Real-time voice interactive digital human, supporting end-to-end voice solutions (GLM-4-Voice - THG) and cas...
Silero Models: pre-trained speech-to-text, text-to-speech and text-enhancement models made embarrassingly simple
Streamer-Sales 销冠 —— 卖货主播 LLM 大模型🛒🎁，一个能够根据给定的商品特点从激发用户购买意愿角度出发进行商品解说的卖货主播大模型。🚀⭐内含详细的数据生成流程❗ 📦另外还集成了 LMDeploy 加速推理🚀、RAG检索增强生成 📚、TTS文字转语音🔊、数字人生成 🦸、 Agent 使用网络查询实时信息🌐、ASR 语音转文字🎙️、Vue 生态搭建前端🍍、F...
OpenAI-Compatible Proxy Middleware for the Wyoming Protocol
ChunkFormer: Masked Chunking Conformer For Long-Form Speech Transcription
呼叫中心，智能客服，智能外呼，大模型呼入机器人，大模型呼出机器人，客服系统，工单系统，开源呼叫中心系统，话务系统，智能外呼系统，智能电话外呼，呼叫中心系统，大模型客服，电话外呼，客服中心，在线客服，大模型呼叫中心，呼入机器人，大模型机器人，智能电话外呼，开源呼叫中心系统，电话外呼，在线客服，大模型callcenter,contactcenter,Call，IPCC，Customer Service...
A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)
Analyze videos using LLMs, Computer Vision and Automatic Speech Recognition
Open-source industrial-grade ASR models supporting Mandarin, Chinese dialects and English, achieving a new SOTA on public Mandarin ASR benchmarks, while also offering outstanding singing lyrics recogn...
百聆 是一个类似GPT-4o的语音对话机器人，通过ASR+LLM+TTS实现，集成DeepSeek R1等优秀大模型，时延低至800ms，Mac等低配置也可运行，支持打断
The media player for language learning, with dual subtitles, AI-generated subtitles, real-time translation, and more!
实时语音交互数字人，支持端到端语音方案（GLM-4-Voice - THG）和级联方案（ASR-LLM-TTS-THG）。可自定义形象与音色，无须训练，支持音色克隆，首包延迟低至3s。Real-time voice interactive digital human, supporting end-to-end voice solutions (GLM-4-Voice - THG) and cas...
Dockerfile for WhisperX: Automatic Speech Recognition with Word-Level Timestamps and Speaker Diarization (Dockerfile, CI image build and test)
Whisper & Faster-Whisper standalone executables for those who don't want to bother with Python.
Speech-to-text, text-to-speech, speaker diarization, speech enhancement, and VAD using next-gen Kaldi with onnxruntime without Internet connection. Support embedded systems, Android, iOS, HarmonyOS, R...
An Optimized Speech-to-Text Pipeline for the Whisper Model Supporting Multiple Inference Engine
Verbatim Automatic Speech Recognition with improved word-level timestamps and filler detection
Running speech to text model (whisper.cpp) in Unity3d on your local machine.
A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)
WhisperX: Automatic Speech Recognition with Word-level Timestamps (& Diarization)
The media player for language learning, with dual subtitles, AI-generated subtitles, real-time translation, and more!
Speech-to-text, text-to-speech, speaker diarization, speech enhancement, and VAD using next-gen Kaldi with onnxruntime without Internet connection. Support embedded systems, Android, iOS, HarmonyOS, R...
Offline speech recognition API for Android, iOS, Raspberry Pi and servers with Python, Java, C# and Node
This is a python API which allows you to get the transcript/subtitles for a given YouTube video. It also works for automatically generated subtitles and it does not require an API key nor a headless b...
Automatic Speech Recognition with Speaker Diarization based on OpenAI Whisper
Whisper & Faster-Whisper standalone executables for those who don't want to bother with Python.
Easy-to-use Speech Toolkit including Self-Supervised Learning model, SOTA/Streaming ASR with punctuation, Streaming TTS with text frontend, Speaker Verification System, End-to-End Speech Translation a...
百聆 是一个类似GPT-4o的语音对话机器人，通过ASR+LLM+TTS实现，集成DeepSeek R1等优秀大模型，时延低至800ms，Mac等低配置也可运行，支持打断
Open-source industrial-grade ASR models supporting Mandarin, Chinese dialects and English, achieving a new SOTA on public Mandarin ASR benchmarks, while also offering outstanding singing lyrics recogn...
Analyze videos using LLMs, Computer Vision and Automatic Speech Recognition
实时语音交互数字人，支持端到端语音方案（GLM-4-Voice - THG）和级联方案（ASR-LLM-TTS-THG）。可自定义形象与音色，无须训练，支持音色克隆，首包延迟低至3s。Real-time voice interactive digital human, supporting end-to-end voice solutions (GLM-4-Voice - THG) and cas...
Real-time speech recognition and voice activity detection (VAD) using next-gen Kaldi with ncnn without Internet connection. Support iOS, Android, Linux, macOS, Windows, Raspberry Pi, VisionFive2, Lich...
Silero Models: pre-trained speech-to-text, text-to-speech and text-enhancement models made embarrassingly simple
OpenAI-Compatible Proxy Middleware for the Wyoming Protocol
The media player for language learning, with dual subtitles, AI-generated subtitles, real-time translation, and more!
An open source chat bot architecture for voice/vision (and multimodal) assistants, local(CPU/GPU bound) and remote(I/O bound) to run.
ChunkFormer: Masked Chunking Conformer For Long-Form Speech Transcription
Speech recognition module for react native using Vosk library
A text-to-speech and speech-to-text server compatible with the OpenAI API, supporting Whisper, FunASR, Bark, and CosyVoice backends.
呼叫中心，智能客服，智能外呼，大模型呼入机器人，大模型呼出机器人，客服系统，工单系统，开源呼叫中心系统，话务系统，智能外呼系统，智能电话外呼，呼叫中心系统，大模型客服，电话外呼，客服中心，在线客服，大模型呼叫中心，呼入机器人，大模型机器人，智能电话外呼，开源呼叫中心系统，电话外呼，在线客服，大模型callcenter,contactcenter,Call，IPCC，Customer Service...
This is an on-CPU real-time conversational system for two-way speech communication with AI models, utilizing a continuous streaming architecture for fluid conversations with immediate responses and na...
Analyze videos using LLMs, Computer Vision and Automatic Speech Recognition
Open-source industrial-grade ASR models supporting Mandarin, Chinese dialects and English, achieving a new SOTA on public Mandarin ASR benchmarks, while also offering outstanding singing lyrics recogn...
BreezeAPP 是一款為 Android 和 iOS 平台開發的純手機 AI 應用程式。從 App Store下載，即可在不連網的狀態下享受多項 AI 功能。源碼由聯發創新基地(MediaTek Research)提供。我們旨在推廣兩個概念: 人人都可以在自己的手機上自由選擇並運行不同的LLM - one is free to choose one's own LLM to run on a ...
百聆 是一个类似GPT-4o的语音对话机器人，通过ASR+LLM+TTS实现，集成DeepSeek R1等优秀大模型，时延低至800ms，Mac等低配置也可运行，支持打断
Dockerfile for WhisperX: Automatic Speech Recognition with Word-Level Timestamps and Speaker Diarization (Dockerfile, CI image build and test)
It includes papers on speech&audio field. Now update: ICLR2023-2025, ICML2023-2024, NeurIPS2023-2024, ACMMM2024, AAAI2024, ACL2024, EMNLP2024, NAACL2025, AAAI2025, IJCAI2024
实时语音交互数字人，支持端到端语音方案（GLM-4-Voice - THG）和级联方案（ASR-LLM-TTS-THG）。可自定义形象与音色，无须训练，支持音色克隆，首包延迟低至3s。Real-time voice interactive digital human, supporting end-to-end voice solutions (GLM-4-Voice - THG) and cas...
Nexa SDK is a comprehensive toolkit for supporting GGML and ONNX models. It supports text generation, image generation, vision-language models (VLM), Audio Language Model, auto-speech-recognition (ASR...
The media player for language learning, with dual subtitles, AI-generated subtitles, real-time translation, and more!
🍦 Speech-AI-Forge is a project developed around TTS generation model, implementing an API Server and a Gradio-based WebUI.
百聆 是一个类似GPT-4o的语音对话机器人，通过ASR+LLM+TTS实现，集成DeepSeek R1等优秀大模型，时延低至800ms，Mac等低配置也可运行，支持打断
StreamSpeech is an “All in One” seamless model for offline and simultaneous speech recognition, speech translation and speech synthesis.
Open-source industrial-grade ASR models supporting Mandarin, Chinese dialects and English, achieving a new SOTA on public Mandarin ASR benchmarks, while also offering outstanding singing lyrics recogn...
实时语音交互数字人，支持端到端语音方案（GLM-4-Voice - THG）和级联方案（ASR-LLM-TTS-THG）。可自定义形象与音色，无须训练，支持音色克隆，首包延迟低至3s。Real-time voice interactive digital human, supporting end-to-end voice solutions (GLM-4-Voice - THG) and cas...
Analyze videos using LLMs, Computer Vision and Automatic Speech Recognition
Verbatim Automatic Speech Recognition with improved word-level timestamps and filler detection
⚡ 一款用于自动语音识别 (ASR)、翻译的高性能异步 API。不需要购买Whisper API，使用本地运行的Whisper模型进行推理，并支持多GPU并发，针对分布式部署进行设计。还内置了包括TikTok、抖音等社交媒体平台的爬虫，可实现来自多个社交平台的无缝媒体处理，为媒体内容数据自动化处理提供了强大且可扩展的解决方案。
This is an on-CPU real-time conversational system for two-way speech communication with AI models, utilizing a continuous streaming architecture for fluid conversations with immediate responses and na...
A text-to-speech and speech-to-text server compatible with the OpenAI API, supporting Whisper, FunASR, Bark, and CosyVoice backends.
LiteASR: Efficient Automatic Speech Recognition with Low-Rank Approximation
BreezeAPP 是一款為 Android 和 iOS 平台開發的純手機 AI 應用程式。從 App Store下載，即可在不連網的狀態下享受多項 AI 功能。源碼由聯發創新基地(MediaTek Research)提供。我們旨在推廣兩個概念: 人人都可以在自己的手機上自由選擇並運行不同的LLM - one is free to choose one's own LLM to run on a ...
WhisperX: Automatic Speech Recognition with Word-level Timestamps (& Diarization)
Speech-to-text, text-to-speech, speaker diarization, speech enhancement, and VAD using next-gen Kaldi with onnxruntime without Internet connection. Support embedded systems, Android, iOS, HarmonyOS, R...
Nexa SDK is a comprehensive toolkit for supporting GGML and ONNX models. It supports text generation, image generation, vision-language models (VLM), Audio Language Model, auto-speech-recognition (ASR...
A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)
Streamer-Sales 销冠 —— 卖货主播 LLM 大模型🛒🎁，一个能够根据给定的商品特点从激发用户购买意愿角度出发进行商品解说的卖货主播大模型。🚀⭐内含详细的数据生成流程❗ 📦另外还集成了 LMDeploy 加速推理🚀、RAG检索增强生成 📚、TTS文字转语音🔊、数字人生成 🦸、 Agent 使用网络查询实时信息🌐、ASR 语音转文字🎙️、Vue 生态搭建前端🍍、F...
Automatic Speech Recognition with Speaker Diarization based on OpenAI Whisper
Offline speech recognition API for Android, iOS, Raspberry Pi and servers with Python, Java, C# and Node
Easy-to-use Speech Toolkit including Self-Supervised Learning model, SOTA/Streaming ASR with punctuation, Streaming TTS with text frontend, Speaker Verification System, End-to-End Speech Translation a...
The media player for language learning, with dual subtitles, AI-generated subtitles, real-time translation, and more!
This is a python API which allows you to get the transcript/subtitles for a given YouTube video. It also works for automatically generated subtitles and it does not require an API key nor a headless b...
Whisper & Faster-Whisper standalone executables for those who don't want to bother with Python.
百聆 是一个类似GPT-4o的语音对话机器人，通过ASR+LLM+TTS实现，集成DeepSeek R1等优秀大模型，时延低至800ms，Mac等低配置也可运行，支持打断
🍦 Speech-AI-Forge is a project developed around TTS generation model, implementing an API Server and a Gradio-based WebUI.
StreamSpeech is an “All in One” seamless model for offline and simultaneous speech recognition, speech translation and speech synthesis.
🤖 wukong-robot 是一个简单、灵活、优雅的中文语音对话机器人/智能音箱项目，支持ChatGPT多轮对话能力，还可能是首个支持脑机交互的开源智能音箱项目。
Open-source industrial-grade ASR models supporting Mandarin, Chinese dialects and English, achieving a new SOTA on public Mandarin ASR benchmarks, while also offering outstanding singing lyrics recogn...
StreamSpeech is an “All in One” seamless model for offline and simultaneous speech recognition, speech translation and speech synthesis.
🍦 Speech-AI-Forge is a project developed around TTS generation model, implementing an API Server and a Gradio-based WebUI.
The media player for language learning, with dual subtitles, AI-generated subtitles, real-time translation, and more!
Open-source industrial-grade ASR models supporting Mandarin, Chinese dialects and English, achieving a new SOTA on public Mandarin ASR benchmarks, while also offering outstanding singing lyrics recogn...
Analyze videos using LLMs, Computer Vision and Automatic Speech Recognition
Streamer-Sales 销冠 —— 卖货主播 LLM 大模型🛒🎁，一个能够根据给定的商品特点从激发用户购买意愿角度出发进行商品解说的卖货主播大模型。🚀⭐内含详细的数据生成流程❗ 📦另外还集成了 LMDeploy 加速推理🚀、RAG检索增强生成 📚、TTS文字转语音🔊、数字人生成 🦸、 Agent 使用网络查询实时信息🌐、ASR 语音转文字🎙️、Vue 生态搭建前端🍍、F...
Praises is a text-to-speech tool that can help you read text easily.
This is an on-CPU real-time conversational system for two-way speech communication with AI models, utilizing a continuous streaming architecture for fluid conversations with immediate responses and na...
It includes papers on speech&audio field. Now update: ICLR2023-2025, ICML2023-2024, NeurIPS2023-2024, ACMMM2024, AAAI2024, ACL2024, EMNLP2024, NAACL2025, AAAI2025, IJCAI2024
💬 Transcribe, translate, diarize, annotate and subtitle video (and audio) with Whisper on Win, Linux and Mac ... fast!
gpt_server是一个用于生产级部署LLMs、Embedding、Reranker、ASR和TTS的开源框架。
Speech-to-text, text-to-speech, speaker diarization, speech enhancement, and VAD using next-gen Kaldi with onnxruntime without Internet connection. Support embedded systems, Android, iOS, HarmonyOS, R...
AI VTuber with LLM, ASR, TTS, OCR, CV and more technologies to live stream or play Minecraft with you.
Gradio WebUI for whisper, faster-whisper, whisper-timestamped. Supports YouTube Downloader, Vocal Remover and Transcription.
ChunkFormer: Masked Chunking Conformer For Long-Form Speech Transcription
Blazing fast whisper turbo for ASR (speech-to-text) tasks
Get started using Deepgram's Live Transcription with this Flask demo app