From 85c1848286e206195a94993b49e8c32117cadc90 Mon Sep 17 00:00:00 2001 From: speech_asr Date: Wed, 15 Mar 2023 15:17:27 +0800 Subject: [PATCH] update --- .../unit_test.py | 7 +++---- funasr/bin/eend_ola_inference.py | 2 +- 2 files changed, 4 insertions(+), 5 deletions(-) diff --git a/egs_modelscope/speaker_diarization/speech_diarization_sond-zh-cn-alimeeting-16k-n16k4-pytorch/unit_test.py b/egs_modelscope/speaker_diarization/speech_diarization_sond-zh-cn-alimeeting-16k-n16k4-pytorch/unit_test.py index 3cb31cfb7..5f4563dbc 100644 --- a/egs_modelscope/speaker_diarization/speech_diarization_sond-zh-cn-alimeeting-16k-n16k4-pytorch/unit_test.py +++ b/egs_modelscope/speaker_diarization/speech_diarization_sond-zh-cn-alimeeting-16k-n16k4-pytorch/unit_test.py @@ -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) diff --git a/funasr/bin/eend_ola_inference.py b/funasr/bin/eend_ola_inference.py index 96e7516e3..2ff7eeff2 100755 --- a/funasr/bin/eend_ola_inference.py +++ b/funasr/bin/eend_ola_inference.py @@ -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,