speech_recognition/FunASR
1
0
Fork 0
mirror of https://github.com/modelscope/FunASR synced 2025-09-15 14:48:36 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

update

Browse Source
This commit is contained in:
speech_asr 2023-03-15 15:17:27 +08:00
parent 2cfe010d7b
commit 85c1848286
2 changed files with 4 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
egs_modelscope/speaker_diarization/speech_diarization_sond-zh-cn-alimeeting-16k-n16k4-pytorch/unit_test.py
View File

@ -14,13 +14,12 @@ inference_diar_pipline = pipeline(
)
# 以 audio_list 作为输入，其中第一个音频为待检测语音，后面的音频为不同说话人的声纹注册语音
audio_list = [[
audio_list = [
"https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_data/record.wav",
"https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_data/spk_A.wav",
"https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_data/spk_B.wav",
"https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_data/spk_B1.wav"
]]
]
results = inference_diar_pipline(audio_in=audio_list)
for rst in results:
print(rst["value"])
print(results)

2
funasr/bin/eend_ola_inference.py
View File

@ -210,7 +210,7 @@ def inference_modelscope(
if data_path_and_name_and_type is None and raw_inputs is not None:
if isinstance(raw_inputs, torch.Tensor):
raw_inputs = raw_inputs.numpy()
data_path_and_name_and_type = [raw_inputs, "speech", "waveform"]
data_path_and_name_and_type = [raw_inputs[0], "speech", "bytes"]
logger.info(data_path_and_name_and_type)
loader = EENDOLADiarTask.build_streaming_iterator(
data_path_and_name_and_type,