Open-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diarization pipelines, and OpenAI-compatible/MCP serving.
Python asraudiochineseemotion-recognitionfunasrmcp-servermultilingual-asropenai-compatible-apiparaformerpunctuationpytorchreal-time-asrspeaker-diarizationspeech-recognitionspeech-to-textstreaming-asrtranscriptionvllmvoice-activity-detectionwhisper-alternative
docs
游雁6d3a3da8a8c7
diff --git a/README.md b/README.mdindex c27ff7ccf..c9eae96e6 100644--- a/README.md+++ b/README.md@@ -60,18 +60,26 @@<a name="Installation"></a>## Installation+- Requirements+```text+python>=3.8+torch>=1.13+torchaudio+```++- Install for pypi```shellpip3 install -U funasr```-Or install from source code+- Or install from source code``` shgit clone https://github.com/alibaba/FunASR.git && cd FunASRpip3 install -e ./```-Install modelscope for the pretrained models (Optional)+- Install modelscope or huggingface_hub for the pretrained models (Optional)```shell-pip3 install -U modelscope+pip3 install -U modelscope huggingface_hub```## Model Zoodiff --git a/README_zh.md b/README_zh.mdindex 6d48137ad..d51fa5ab6 100644--- a/README_zh.md+++ b/README_zh.md@@ -64,14 +64,24 @@ FunASR希望在语音识别的学术研究和工业应用之间架起一座桥<a name="安装教程"></a>## 安装教程+- 安装funasr之前,确保已经安装了下面依赖环境:+```text+python>=3.8+torch>=1.13+torchaudio+```++- pip安装```shellpip3 install -U funasr```-或者从源代码安装++- 或者从源代码安装``` shgit clone https://github.com/alibaba/FunASR.git && cd FunASRpip3 install -e ./```+如果需要使用工业预训练模型,安装modelscope与huggingface_hub(可选)```shell