mirror of
https://github.com/modelscope/FunASR
synced 2025-09-15 14:48:36 +08:00
702ec03ad8
* add hotword for deploy_tools * Support wfst decoder and contextual biasing (#1039) * Support wfst decoder and contextual biasing * Turn on fstbin compilation --------- Co-authored-by: gongbo.gb <gongbo.gb@alibaba-inc.com> * mv funasr/runtime runtime * Fix crash caused by OOV in hotwords list * funasr infer * funasr infer * funasr infer * funasr infer * funasr infer * fix some bugs about fst hotword; support wfst for websocket server and clients; mv runtime out of funasr; modify relative docs * del onnxruntime/include/gflags * update tensor.h * update run_server.sh * update deploy tools * update deploy tools * update websocket-server * update funasr-wss-server * Remove self loop propagation * Update websocket_protocol_zh.md * Update websocket_protocol_zh.md * update hotword protocol * author zhaomingwork: change hotwords for h5 and java * update hotword protocol * catch exception for json_fst_hws * update hotword on message * update onnx benchmark for ngram&hotword * update docs * update funasr-wss-serve * add NONE for LM_DIR * update docs * update run_server.sh * add whats-new * modify whats-new * update whats-new * update whats-new * Support decoder option for beam searching * update benchmark_onnx_cpp * Support decoder option for websocket * fix bug of CompileHotwordEmbedding * update html client * update docs --------- Co-authored-by: gongbo.gb <35997837+aibulamusi@users.noreply.github.com> Co-authored-by: gongbo.gb <gongbo.gb@alibaba-inc.com> Co-authored-by: 游雁 <zhifu.gzf@alibaba-inc.com>
28 lines
930 B
Python
28 lines
930 B
Python
from funasr_onnx import Fsmn_vad_online
|
|
import soundfile
|
|
from pathlib import Path
|
|
|
|
model_dir = "damo/speech_fsmn_vad_zh-cn-16k-common-pytorch"
|
|
wav_path = '{}/.cache/modelscope/hub/damo/speech_fsmn_vad_zh-cn-16k-common-pytorch/example/vad_example.wav'.format(Path.home())
|
|
|
|
model = Fsmn_vad_online(model_dir)
|
|
|
|
|
|
##online vad
|
|
speech, sample_rate = soundfile.read(wav_path)
|
|
speech_length = speech.shape[0]
|
|
#
|
|
sample_offset = 0
|
|
step = 1600
|
|
param_dict = {'in_cache': []}
|
|
for sample_offset in range(0, speech_length, min(step, speech_length - sample_offset)):
|
|
if sample_offset + step >= speech_length - 1:
|
|
step = speech_length - sample_offset
|
|
is_final = True
|
|
else:
|
|
is_final = False
|
|
param_dict['is_final'] = is_final
|
|
segments_result = model(audio_in=speech[sample_offset: sample_offset + step],
|
|
param_dict=param_dict)
|
|
if segments_result:
|
|
print(segments_result) |