语音识别(音频转文本)

Vosk

python常用代码块 | python多种方式实现语音转文字_python 音频转文字-优快云博客

模型下载

VOSK Models

OpenAI的Whisper模型

Whisper是OpenAI推出的一个多语言、端到端的语音识别模型，它能在多种情境下进行语音理解，包括跨语言对话、混合语言输入等。而Vosk则是一个轻量级的离线语音识别引擎，特别适合于资源有限的环境或对实时性要求高的场景。

whisper

https://stackoverflow.com/questions/75464443/python-cant-import-whisper-ctypes-util-find-libraryc-returns-none

集团   离线语音转写

https://ai.crc.com.cn/#/offlineVoiceTranscription

SpeechRecognition

pocketsphinx

【小沐学Python】Python实现语音识别（SpeechRecognition）_python 语音识别-优快云博客

下载 cmusphinx-zh-cn-5.2.tar.gz

https://download.youkuaiyun.com/download/linmy3303/12206301?utm_medium=distribute.pc_relevant_download.none-task-download-2~default~LANDING_RERANK~Rate-4-12206301-download-12195191.257%5Ev16%5Epc_dl_relevant_base1_a&depth_1-utm_source=distribute.pc_relevant_download.none-task-download-2~default~LANDING_RERANK~Rate-4-12206301-download-12195191.257%5Ev16%5Epc_dl_relevant_base1_a&spm=1003.2020.3001.6616.4

paddlespeech

GitHub - PaddlePaddle/PaddleSpeech: 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 and Keyword Spotting. Won NAACL2022 Best Demo Award.

语音识别-DeepASR

语音识别DeepASR_飞桨-源于产业实践的开源深度学习平台

模型下载

PaddleSpeech/docs/source/released_model.md at develop · PaddlePaddle/PaddleSpeech · GitHub

WeNet

出门问问公司

补全标点符号

Python使用PaddleSpeech实现语音识别（ASR）、语音合成（TTS）-优快云博客

离线部署

离线部署paddlespeech语音识别模型_paddlespeech离线部署-优快云博客

pip安装报错: Microsoft Visual C++ 14.0 or greater is required.

pip安装报错: Microsoft Visual C++ 14.0 or greater is required. Get it with “Microsoft C++ Build Tools“-优快云博客

声纹识别

基于PaddlePaddle实现声纹识别 - 飞桨AI Studio星河社区