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
python runtime
游雁a33bc50e7862
diff --git a/examples/industrial_data_pretraining/sense_voice/demo_libtorch.py b/examples/industrial_data_pretraining/sense_voice/demo_libtorch.pynew file mode 100644index 000000000..530fdfa70--- /dev/null+++ b/examples/industrial_data_pretraining/sense_voice/demo_libtorch.py@@ -0,0 +1,18 @@+#!/usr/bin/env python3+# -*- encoding: utf-8 -*-+# Copyright FunASR (https://github.com/FunAudioLLM/SenseVoice). All Rights Reserved.+# MIT License (https://opensource.org/licenses/MIT)++from pathlib import Path+from funasr_torch import SenseVoiceSmall+from funasr_torch.utils.postprocess_utils import rich_transcription_postprocess+++model_dir = "iic/SenseVoiceSmall"++model = SenseVoiceSmall(model_dir, batch_size=10, device="cuda:0")++wav_or_scp = ["{}/.cache/modelscope/hub/{}/example/en.mp3".format(Path.home(), model_dir)]++res = model(wav_or_scp, language="auto", use_itn=True)+print([rich_transcription_postprocess(i) for i in res])diff --git a/examples/industrial_data_pretraining/sense_voice/demo_onnx.py b/examples/industrial_data_pretraining/sense_voice/demo_onnx.pynew file mode 100644index 000000000..f12072875--- /dev/null+++ b/examples/industrial_data_pretraining/sense_voice/demo_onnx.py@@ -0,0 +1,19 @@+#!/usr/bin/env python3+# -*- encoding: utf-8 -*-+# Copyright FunASR (https://github.com/FunAudioLLM/SenseVoice). All Rights Reserved.+# MIT License (https://opensource.org/licenses/MIT)++from pathlib import Path+from funasr_onnx import SenseVoiceSmall+from funasr_onnx.utils.postprocess_utils import rich_transcription_postprocess+++model_dir = "iic/SenseVoiceSmall"++model = SenseVoiceSmall(model_dir, batch_size=10, quantize=True)++# inference+wav_or_scp = ["{}/.cache/modelscope/hub/{}/example/en.mp3".format(Path.home(), model_dir)]++res = model(wav_or_scp, language="auto", use_itn=True)+print([rich_transcription_postprocess(i) for i in res])