update unittest

speech_asr

2023-03-10 401d6949fe043fb9cd3bf47367339d5f464c2b2f

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
import unittest
 
from modelscope.pipelines import pipeline
from modelscope.utils.constant import Tasks
from modelscope.utils.logger import get_logger
 
logger = get_logger()
 
 
class TestConformerInferencePipelines(unittest.TestCase):
    def test_funasr_path(self):
        import funasr
        import os
        logger.info("run_dir:{0} ; funasr_path: {1}".format(os.getcwd(), funasr.__file__))
 
    def test_aishell1(self):
        inference_pipeline = pipeline(
            task=Tasks.auto_speech_recognition,
            model='damo/speech_conformer_asr_nat-zh-cn-16k-aishell1-vocab4234-pytorch')
        rec_result = inference_pipeline(
            audio_in='https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav')
        logger.info("asr inference result: {0}".format(rec_result))
 
    def test_aishell2(self):
        inference_pipeline = pipeline(
            task=Tasks.auto_speech_recognition,
            model='damo/speech_conformer_asr_nat-zh-cn-16k-aishell2-vocab5212-pytorch')
        rec_result = inference_pipeline(
            audio_in='https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav')
        logger.info("asr inference result: {0}".format(rec_result))
 
 
class TestData2vecInferencePipelines(unittest.TestCase):
    def test_funasr_path(self):
        import funasr
        import os
        logger.info("run_dir:{0} ; funasr_path: {1}".format(os.getcwd(), funasr.__file__))
 
    def test_transformer(self):
        inference_pipeline = pipeline(
            task=Tasks.auto_speech_recognition,
            model='damo/speech_data2vec_pretrain-zh-cn-aishell2-16k-pytorch')
        rec_result = inference_pipeline(
            audio_in='https://modelscope.oss-cn-beijing.aliyuncs.com/test/audios/asr_example.wav')
        logger.info("asr inference result: {0}".format(rec_result))
 
    def test_paraformer(self):
        inference_pipeline = pipeline(
            task=Tasks.auto_speech_recognition,
            model='damo/speech_data2vec_pretrain-paraformer-zh-cn-aishell2-16k')
        rec_result = inference_pipeline(
            audio_in='https://modelscope.oss-cn-beijing.aliyuncs.com/test/audios/asr_example.wav')
        logger.info("asr inference result: {0}".format(rec_result))
 
 
class TestMfccaInferencePipelines(unittest.TestCase):
    def test_funasr_path(self):
        import funasr
        import os
        logger.info("run_dir:{0} ; funasr_path: {1}".format(os.getcwd(), funasr.__file__))
 
    def test_alimeeting(self):
        inference_pipeline = pipeline(
            task=Tasks.auto_speech_recognition,
            model='NPU-ASLP/speech_mfcca_asr-zh-cn-16k-alimeeting-vocab4950',
            model_revision='v3.0.0')
        rec_result = inference_pipeline(
            audio_in='16:32https://pre.modelscope.cn/api/v1/models/NPU-ASLP/speech_mfcca_asr-zh-cn-16k-alimeeting-vocab4950/repo?Revision=master&FilePath=example/asr_example_mc.wav')
        logger.info("asr inference result: {0}".format(rec_result))
 
 
class TestParaformerInferencePipelines(unittest.TestCase):
    def test_funasr_path(self):
        import funasr
        import os
        logger.info("run_dir:{0} ; funasr_path: {1}".format(os.getcwd(), funasr.__file__))
 
    def test_paraformer_large_contextual_common(self):
        param_dict = dict()
        param_dict['hotword'] = "https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/hotword.txt"
        inference_pipeline = pipeline(
            task=Tasks.auto_speech_recognition,
            model='damo/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404',
            param_dict=param_dict)
        rec_result = inference_pipeline(
            audio_in='https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_hotword.wav')
        logger.info("asr inference result: {0}".format(rec_result))
 
    def test_paraformer_large_aishell1(self):
        inference_pipeline = pipeline(
            task=Tasks.auto_speech_recognition,
            model='damo/speech_paraformer-large_asr_nat-zh-cn-16k-aishell1-vocab8404-pytorch')
        rec_result = inference_pipeline(
            audio_in='https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav')
        logger.info("asr inference result: {0}".format(rec_result))
 
    def test_paraformer_large_aishell2(self):
        inference_pipeline = pipeline(
            task=Tasks.auto_speech_recognition,
            model='damo/speech_paraformer-large_asr_nat-zh-cn-16k-aishell2-vocab8404-pytorch')
        rec_result = inference_pipeline(
            audio_in='https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav')
        logger.info("asr inference result: {0}".format(rec_result))
 
    def test_paraformer_large_common(self):
        inference_pipeline = pipeline(
            task=Tasks.auto_speech_recognition,
            model='damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch')
        rec_result = inference_pipeline(
            audio_in='https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav')
        logger.info("asr inference result: {0}".format(rec_result))
 
 
if __name__ == '__main__':
    unittest.main()