From d2755f476872da773b816b3952acef97e1ee9336 Mon Sep 17 00:00:00 2001
From: lzr265946 <lzr265946@alibaba-inc.com>
Date: 星期三, 15 二月 2023 14:37:48 +0800
Subject: [PATCH] add infer aishell1 subtest demo in paraformer-large-contextual
---
egs_modelscope/asr/paraformer/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404/infer.py | 2 +-
egs_modelscope/asr/paraformer/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404/infer_aishell1_subtest_demo.py | 36 ++++++++++++++++++++++++++++++++++++
2 files changed, 37 insertions(+), 1 deletions(-)
diff --git a/egs_modelscope/asr/paraformer/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404/infer.py b/egs_modelscope/asr/paraformer/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404/infer.py
index 78fb8f1..16a57e9 100644
--- a/egs_modelscope/asr/paraformer/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404/infer.py
+++ b/egs_modelscope/asr/paraformer/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404/infer.py
@@ -6,7 +6,7 @@
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
diff --git a/egs_modelscope/asr/paraformer/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404/infer_aishell1_subtest_demo.py b/egs_modelscope/asr/paraformer/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404/infer_aishell1_subtest_demo.py
new file mode 100644
index 0000000..18897b1
--- /dev/null
+++ b/egs_modelscope/asr/paraformer/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404/infer_aishell1_subtest_demo.py
@@ -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)
--
Gitblit v1.9.1