Alternatives and similar repositories for ASR-2Pass

Users that are interested in ASR-2Pass are comparing it to the libraries listed below

• lovemefan / fsmn-vad
  A enterprise-grade Voice Activity Detector from modelscope and funasr.
  ☆125Updated 2 years ago
• peilongchencc / My-FunASR
  基于FunASR实现语音识别，包含常规版和ONNX版(推荐)。
  ☆48Updated last year
• chenyangMl / keyword-spot
  端到端语音唤醒工具箱，从模型训练到模型推理。
  ☆151Updated 5 months ago
• lovemefan / telespeech-asr-python
  ☆69Updated last year
• lovemefan / CT-Transformer-punctuation
  A enterprise-grade Chinese-English code switch punctuator from funasr.
  ☆29Updated last year
• lovemefan / paraformer-python
  paraformer(chinense asr) online onnx runtime for python
  ☆53Updated last year
• modelscope / kws-training-suite
  ☆148Updated 2 years ago
• lovemefan / SenseVoice-python
  SenseVoice-python: A enterprise-grade open source multi-language asr system from funasr opensource with onnxruntime
  ☆108Updated 3 months ago
• pika-online / funasr_seaco_paraformer_onnx_with_timestamp
  修复funasr中seaco-paraformer导出onnx后没有时间戳的bug
  ☆24Updated last year
• pengzhendong / pysilero
  Python Wrapper of Silero VAD
  ☆64Updated 8 months ago
• Tzenthin / wenet_mnn
  语音识别模型pytorch转ONNX转MNN，C++实现部署
  ☆83Updated 3 years ago
• xinchen-ai / Westlake-Omni
  ☆204Updated last year
• yrom / finetune-index-tts
  IndexTTS Fine-tuning notebooks
  ☆133Updated 7 months ago
• xphh / fireredasr-streaming
  low-latency realtime ASR based on FireRedASR
  ☆56Updated 6 months ago
• xiaomingnio / kantts
  TTS appalication based on modelscope KAN-TTS
  ☆41Updated last year
• DakeQQ / Voice-Activity-Detection-VAD-ONNX
  Utilizes ONNX Runtime for speech activity detection.
  ☆41Updated last month
• yeyupiaoling / PunctuationModel
  中文标点符号模型，可以给文本添加标点符号。
  ☆147Updated last year
• hexisyztem / CosyVoice
  Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.
  ☆20Updated 9 months ago
• ywh-my / Easy-Finetune-Bert-VITS2
  Bert-VITS2项目bug多且教程不友好。本proj尽可能修复了Bert-vits2项目的bug，并且可一键启动训练。仅需50条目标说话人语音，获得稳定、快速的TTS模型。
  ☆66Updated 5 months ago
• MooreThreads / MooER
  MooER: Moore-threads Open Omni model for speech-to-speech intERaction. MooER-omni includes a series of end-to-end speech interaction mode…
  ☆219Updated last year
• yeyupiaoling / VoiceprintRecognition-PaddlePaddle
  本项目使用了EcapaTdnn、ResNetSE、ERes2Net、CAM++等多种先进的声纹识别模型，同时本项目也支持了MelSpectrogram、Spectrogram、MFCC、Fbank等多种数据预处理方法
  ☆304Updated last month
• Executedone / Chinese-FastSpeech2
  基于标贝数据继续训练，同时对原本的FastSpeech2模型做了改进，引入了韵律表征以及韵律预测模块，使中文发音更生动且富有节奏
  ☆277Updated 2 years ago
• DakeQQ / Audio-Denoiser-ONNX
  Utilizes ONNX Runtime for audio denoising.
  ☆113Updated last month
• tomer9080 / CarelessWhisper-Streaming
  Causal streaming adaptation of OpenAI Whisper for real-time transcription on small audio chunks.
  ☆62Updated 4 months ago
• WGS-note / F5_TTS_Faster
  F5-TTS 推理加速，速度提升约4倍！
  ☆122Updated last year
• mozillazg / pypinyin-g2pW
  基于 g2pW 提升 pypinyin 的准确性
  ☆103Updated 2 years ago
• pengzhendong / streaming-ChatTTS
  ☆23Updated last year
• jingzhunxue / flow_mirror
  flow mirror models from JZX AI Labs
  ☆43Updated last year
• pengzhendong / streaming-sensevoice
  Pseudo Streaming SenseVoice with Hotwords
  ☆423Updated 10 months ago
• pengzhendong / g2p-mix
  Grapheme-to-Phoneme for Mixed Chinese (Mandarin or Cantonese) and English.
  ☆114Updated 2 months ago