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

add infer aishell1 subtest demo in paraformer-large-contextual

Browse Source
This commit is contained in:
lzr265946 2023-02-15 14:37:48 +08:00
parent 5f63cb783d
commit d2755f4768
2 changed files with 37 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
egs_modelscope/asr/paraformer/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404/infer.py
View File

@ -6,7 +6,7 @@ if __name__ == '__main__':
param_dict = dict()
param_dict['hotword'] = "https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/hotword.txt"
audio_in = "//isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_hotword.wav"
audio_in = "https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_hotword.wav"
output_dir = None
batch_size = 1

36
egs_modelscope/asr/paraformer/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404/infer_aishell1_subtest_demo.py Normal file
View File

@ -0,0 +1,36 @@
import os
import tempfile
import codecs
from modelscope.pipelines import pipeline
from modelscope.utils.constant import Tasks
from modelscope.msdatasets import MsDataset
if __name__ == '__main__':
param_dict = dict()
param_dict['hotword'] = "https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/hotword.txt"
output_dir = "./output"
batch_size = 1
# dataset split ['test']
ds_dict = MsDataset.load(dataset_name='speech_asr_aishell1_hotwords_testsets', namespace='speech_asr')
work_dir = tempfile.TemporaryDirectory().name
if not os.path.exists(work_dir):
os.makedirs(work_dir)
wav_file_path = os.path.join(work_dir, "wav.scp")
with codecs.open(wav_file_path, 'w') as fin:
for line in ds_dict:
wav = line["Audio:FILE"]
idx = wav.split("/")[-1].split(".")[0]
fin.writelines(idx + " " + wav + "\n")
audio_in = wav_file_path
inference_pipeline = pipeline(
task=Tasks.auto_speech_recognition,
model="damo/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404",
output_dir=output_dir,
batch_size=batch_size,
param_dict=param_dict)
rec_result = inference_pipeline(audio_in=audio_in)