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: add torch+torchaudio to install instructions (not in pip deps, user must install separately)
zhifu gao0e9d53e1c74c
diff --git a/README.md b/README.mdindex 28bc3a399..e5b52b90d 100644--- a/README.md+++ b/README.md@@ -33,6 +33,7 @@No local setup? Open the [Colab quickstart](./examples/colab/) to transcribe a public sample or upload your own audio in a browser.```bash+pip install torch torchaudiopip install funasr```@@ -115,6 +116,7 @@ Trying FunASR for the first time? Use the [Colab quickstart](./examples/colab/)## Installation```bash+pip install torch torchaudiopip install funasr```@@ -124,7 +126,7 @@ pip install funasrgit clone https://github.com/modelscope/FunASR.git && cd FunASRpip install -e ./```-Requirements: Python ≥ 3.8, PyTorch ≥ 1.13, torchaudio+Requirements: Python ≥ 3.8. Install [PyTorch + torchaudio](https://pytorch.org/get-started/locally/) first (matching your CUDA version), then `pip install funasr`.</details>@@ -182,8 +184,9 @@ result = model.generate(input="audio.wav", granularity="utterance")```bash# OpenAI-compatible API (recommended)-pip install funasr fastapi uvicorn python-multipart-funasr-server --model sensevoice --device cuda+pip install torch torchaudio+pip install funasr vllm fastapi uvicorn python-multipart+funasr-server --device cuda# → POST /v1/audio/transcriptions at localhost:8000```