Merge pull request #473 from alibaba-damo-academy/dev_smohan

jmwang66

2023-05-09 8dab6d184a034ca86eafa644ea0d2100aadfe27d

 tests/test_asr_inference_pipeline.py

@@ -43,6 +43,7 @@
        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))
        assert rec_result["text"] == "每一天都要快乐喔"

    def test_paraformer(self):
        inference_pipeline = pipeline(
@@ -51,6 +52,7 @@
        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))
        assert rec_result["text"] == "每一天都要快乐喔"


class TestMfccaInferencePipelines(unittest.TestCase):
@@ -65,7 +67,7 @@
            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')
            audio_in='https://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))


@@ -106,6 +108,22 @@
        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))

    def test_paraformer_large_online_common(self):
        inference_pipeline = pipeline(
            task=Tasks.auto_speech_recognition,
            model='damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online')
        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_online_common(self):
        inference_pipeline = pipeline(
            task=Tasks.auto_speech_recognition,
            model='damo/speech_paraformer_asr_nat-zh-cn-16k-common-vocab8404-online')
        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))
@@ -359,6 +377,115 @@
            param_dict={"decoding_model": "offline"})
        logger.info("asr inference result: {0}".format(rec_result))

    def test_uniasr_2pass_pt_common_offline(self):
        inference_pipeline = pipeline(
            task=Tasks.auto_speech_recognition,
            model='damo/speech_UniASR_asr_2pass-pt-16k-common-vocab1617-tensorflow1-offline')
        rec_result = inference_pipeline(
            audio_in='https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_pt.wav',
            param_dict={"decoding_model": "offline"})
        logger.info("asr inference result: {0}".format(rec_result))

    def test_uniasr_2pass_pt_common_online(self):
        inference_pipeline = pipeline(
            task=Tasks.auto_speech_recognition,
            model='damo/speech_UniASR_asr_2pass-pt-16k-common-vocab1617-tensorflow1-online')
        rec_result = inference_pipeline(
            audio_in='https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_pt.wav',
            param_dict={"decoding_model": "normal"})
        logger.info("asr inference result: {0}".format(rec_result))
    
    def test_uniasr_2pass_ru_common_offline(self):
        inference_pipeline = pipeline(
            task=Tasks.auto_speech_recognition,
            model='damo/speech_UniASR_asr_2pass-ru-16k-common-vocab1664-tensorflow1-offline')
        rec_result = inference_pipeline(
            audio_in='https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_ru.wav',
            param_dict={"decoding_model": "offline"})
        logger.info("asr inference result: {0}".format(rec_result))

    def test_uniasr_2pass_ru_common_online(self):
        inference_pipeline = pipeline(
            task=Tasks.auto_speech_recognition,
            model='damo/speech_UniASR_asr_2pass-ru-16k-common-vocab1664-tensorflow1-online')
        rec_result = inference_pipeline(
            audio_in='https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_ru.wav',
            param_dict={"decoding_model": "normal"})
        logger.info("asr inference result: {0}".format(rec_result))

    def test_uniasr_2pass_vi_common_offline(self):
        inference_pipeline = pipeline(
            task=Tasks.auto_speech_recognition,
            model='damo/speech_UniASR_asr_2pass-vi-16k-common-vocab1001-pytorch-offline')
        rec_result = inference_pipeline(
            audio_in='https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_vi.wav',
            param_dict={"decoding_model": "offline"})
        logger.info("asr inference result: {0}".format(rec_result))

    def test_uniasr_2pass_vi_common_online(self):
        inference_pipeline = pipeline(
            task=Tasks.auto_speech_recognition,
            model='damo/speech_UniASR_asr_2pass-vi-16k-common-vocab1001-pytorch-online')
        rec_result = inference_pipeline(
            audio_in='https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_vi.wav',
            param_dict={"decoding_model": "normal"})
        logger.info("asr inference result: {0}".format(rec_result))

    def test_uniasr_2pass_zhcn_8k_common_vocab3445_offline(self):
        inference_pipeline = pipeline(
            task=Tasks.auto_speech_recognition,
            model='damo/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab3445-pytorch-offline')
        rec_result = inference_pipeline(
            audio_in='https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav',
            param_dict={"decoding_model": "offline"})
        logger.info("asr inference result: {0}".format(rec_result))

    def test_uniasr_2pass_zhcn_8k_common_vocab3445_online(self):
        inference_pipeline = pipeline(
            task=Tasks.auto_speech_recognition,
            model='damo/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab3445-pytorch-online')
        rec_result = inference_pipeline(
            audio_in='https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav',
            param_dict={"decoding_model": "normal"})
        logger.info("asr inference result: {0}".format(rec_result))

    def test_uniasr_2pass_zhcn_8k_common_vocab8358_offline(self):
        inference_pipeline = pipeline(
            task=Tasks.auto_speech_recognition,
            model='damo/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab8358-tensorflow1-offline')
        rec_result = inference_pipeline(
            audio_in='https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav',
            param_dict={"decoding_model": "offline"})
        logger.info("asr inference result: {0}".format(rec_result))

    def test_uniasr_2pass_zhcn_8k_common_vocab8358_online(self):
        inference_pipeline = pipeline(
            task=Tasks.auto_speech_recognition,
            model='damo/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab8358-tensorflow1-online')
        rec_result = inference_pipeline(
            audio_in='https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav',
            param_dict={"decoding_model": "normal"})
        logger.info("asr inference result: {0}".format(rec_result))

    def test_uniasr_2pass_zhcn_16k_common_vocab8358_offline(self):
        inference_pipeline = pipeline(
            task=Tasks.auto_speech_recognition,
            model='damo/speech_UniASR_asr_2pass-zh-cn-16k-common-vocab8358-tensorflow1-offline')
        rec_result = inference_pipeline(
            audio_in='https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav',
            param_dict={"decoding_model": "offline"})
        logger.info("asr inference result: {0}".format(rec_result))

    def test_uniasr_2pass_zhcn_16k_common_vocab8358_online(self):
        inference_pipeline = pipeline(
            task=Tasks.auto_speech_recognition,
            model='damo/speech_UniASR_asr_2pass-zh-cn-16k-common-vocab8358-tensorflow1-online')
        rec_result = inference_pipeline(
            audio_in='https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav',
            param_dict={"decoding_model": "normal"})
        logger.info("asr inference result: {0}".format(rec_result))



if __name__ == '__main__':
    unittest.main()