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
add demo.py for all kws models (#2107)
sugarcase8cd8e25f180b
diff --git a/examples/industrial_data_pretraining/fsmn_kws/demo.py b/examples/industrial_data_pretraining/fsmn_kws/demo.pynew file mode 100644index 000000000..6bac47bbe--- /dev/null+++ b/examples/industrial_data_pretraining/fsmn_kws/demo.py@@ -0,0 +1,18 @@+#!/usr/bin/env python3+# -*- encoding: utf-8 -*-+# Copyright FunASR (https://github.com/alibaba-damo-academy/FunASR). All Rights Reserved.+# MIT License (https://opensource.org/licenses/MIT)++from funasr import AutoModel++model = AutoModel(+ model="iic/speech_charctc_kws_phone-xiaoyun",+ keywords="小云小云",+ output_dir="./outputs/debug",+ device='cpu'+)++test_wav = "https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/KWS/pos_testset/kws_xiaoyunxiaoyun.wav"++res = model.generate(input=test_wav, cache={},)+print(res)diff --git a/examples/industrial_data_pretraining/fsmn_kws_mt/demo.py b/examples/industrial_data_pretraining/fsmn_kws_mt/demo.pynew file mode 100644index 000000000..6bac47bbe--- /dev/null+++ b/examples/industrial_data_pretraining/fsmn_kws_mt/demo.py@@ -0,0 +1,18 @@+#!/usr/bin/env python3+# -*- encoding: utf-8 -*-+# Copyright FunASR (https://github.com/alibaba-damo-academy/FunASR). All Rights Reserved.+# MIT License (https://opensource.org/licenses/MIT)++from funasr import AutoModel++model = AutoModel(+ model="iic/speech_charctc_kws_phone-xiaoyun",+ keywords="小云小云",+ output_dir="./outputs/debug",+ device='cpu'+)++test_wav = "https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/KWS/pos_testset/kws_xiaoyunxiaoyun.wav"++res = model.generate(input=test_wav, cache={},)+print(res)diff --git a/examples/industrial_data_pretraining/sanm_kws/demo.py b/examples/industrial_data_pretraining/sanm_kws/demo.pynew file mode 100644index 000000000..78f8c21a7--- /dev/null+++ b/examples/industrial_data_pretraining/sanm_kws/demo.py@@ -0,0 +1,18 @@+#!/usr/bin/env python3+# -*- encoding: utf-8 -*-+# Copyright FunASR (https://github.com/alibaba-damo-academy/FunASR). All Rights Reserved.+# MIT License (https://opensource.org/licenses/MIT)++from funasr import AutoModel++model = AutoModel(+ model="iic/speech_sanm_kws_phone-xiaoyun-commands-offline",+ keywords="小云小云",+ output_dir="./outputs/debug",+ device='cpu'+)++test_wav = "https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/KWS/pos_testset/kws_xiaoyunxiaoyun.wav"++res = model.generate(input=test_wav, cache={},)+print(res)diff --git a/examples/industrial_data_pretraining/sanm_kws_streaming/demo.py b/examples/industrial_data_pretraining/sanm_kws_streaming/demo.pynew file mode 100644index 000000000..013d6e327--- /dev/null+++ b/examples/industrial_data_pretraining/sanm_kws_streaming/demo.py@@ -0,0 +1,21 @@+#!/usr/bin/env python3+# -*- encoding: utf-8 -*-+# Copyright FunASR (https://github.com/alibaba-damo-academy/FunASR). All Rights Reserved.+# MIT License (https://opensource.org/licenses/MIT)++from funasr import AutoModel++model = AutoModel(+ model="iic/speech_sanm_kws_phone-xiaoyun-commands-online",+ keywords="小云小云",+ output_dir="./outputs/debug",+ device='cpu',+ chunk_size=[4, 8, 4],+ encoder_chunk_look_back=0,+ decoder_chunk_look_back=0,+)++test_wav = "https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/KWS/pos_testset/kws_xiaoyunxiaoyun.wav"++res = model.generate(input=test_wav, cache={},)+print(res)