update unittest

speech_asr

2023-03-10 c0b48ccf6af5d8edf0a0912564257a08eab4fd4b

 tests/test_asr_inference_pipeline.py

@@ -110,6 +110,228 @@
            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_tiny_commandword(self):
        inference_pipeline = pipeline(
            task=Tasks.auto_speech_recognition,
            model='damo/speech_paraformer-tiny-commandword_asr_nat-zh-cn-16k-vocab544-pytorch')
        rec_result = inference_pipeline(
            audio_in='https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh_command.wav')
        logger.info("asr inference result: {0}".format(rec_result))

    def test_paraformer_8k(self):
        inference_pipeline = pipeline(
            task=Tasks.auto_speech_recognition,
            model='damo/speech_paraformer_asr_nat-zh-cn-8k-common-vocab8358-tensorflow1')
        rec_result = inference_pipeline(
            audio_in='https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_8K.wav')
        logger.info("asr inference result: {0}".format(rec_result))

    def test_paraformer_aishell1(self):
        inference_pipeline = pipeline(
            task=Tasks.auto_speech_recognition,
            model='damo/speech_paraformer_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_paraformer_aishell2(self):
        inference_pipeline = pipeline(
            task=Tasks.auto_speech_recognition,
            model='damo/speech_paraformer_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 TestParaformerBertInferencePipelines(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_paraformerbert_asr_nat-zh-cn-16k-aishell1-vocab4234-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_aishell2(self):
        inference_pipeline = pipeline(
            task=Tasks.auto_speech_recognition,
            model='damo/speech_paraformerbert_asr_nat-zh-cn-16k-aishell2-vocab5212-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))


class TestUniasrInferencePipelines(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_uniasr_2pass_cantonese_chs_16k_common_offline(self):
        inference_pipeline = pipeline(
            task=Tasks.auto_speech_recognition,
            model='damo/speech_UniASR_asr_2pass-cantonese-CHS-16k-common-vocab1468-tensorflow1-online')
        rec_result = inference_pipeline(
            audio_in='https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_cantonese-CHS.wav',
            param_dict={"decoding_model": "offline"})
        logger.info("asr inference result: {0}".format(rec_result))

    def test_uniasr_2pass_cantonese_chs_16k_common_online(self):
        inference_pipeline = pipeline(
            task=Tasks.auto_speech_recognition,
            model='damo/speech_UniASR_asr_2pass-cantonese-CHS-16k-common-vocab1468-tensorflow1-online')
        rec_result = inference_pipeline(
            audio_in='https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_cantonese-CHS.wav',
            param_dict={"decoding_model":"normal"})
        logger.info("asr inference result: {0}".format(rec_result))

    def test_uniasr_2pass_cn_dialect_offline(self):
        inference_pipeline = pipeline(
            task=Tasks.auto_speech_recognition,
            model='damo/speech_UniASR_asr_2pass-cn-dialect-16k-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')
        logger.info("asr inference result: {0}".format(rec_result))
    
    def test_uniasr_2pass_cn_dialect_online(self):
        inference_pipeline = pipeline(
            task=Tasks.auto_speech_recognition,
            model='damo/speech_UniASR_asr_2pass-cn-dialect-16k-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')
        logger.info("asr inference result: {0}".format(rec_result))

    def test_uniasr_2pass_de_common_offline(self):
        inference_pipeline = pipeline(
            task=Tasks.auto_speech_recognition,
            model='damo/speech_UniASR_asr_2pass-de-16k-common-vocab3690-tensorflow1-offline')
        rec_result = inference_pipeline(
            audio_in='https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_de.wav',
            param_dict={"decoding_model":"offline"})
        logger.info("asr inference result: {0}".format(rec_result))

    def test_uniasr_2pass_de_common_online(self):
        inference_pipeline = pipeline(
            task=Tasks.auto_speech_recognition,
            model='damo/speech_UniASR_asr_2pass-de-16k-common-vocab3690-tensorflow1-online')
        rec_result = inference_pipeline(
            audio_in='https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_de.wav',
            param_dict={"decoding_model":"normal"})
        logger.info("asr inference result: {0}".format(rec_result))

    def test_uniasr_2pass_en_common_offline(self):
        inference_pipeline = pipeline(
            task=Tasks.auto_speech_recognition,
            model='damo/speech_UniASR_asr_2pass-en-16k-common-vocab1080-tensorflow1-offline')
        rec_result = inference_pipeline(
            audio_in='https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_en.wav',
            param_dict={"decoding_model":"offline"})
        logger.info("asr inference result: {0}".format(rec_result))

    def test_uniasr_2pass_en_common_online(self):
        inference_pipeline = pipeline(
            task=Tasks.auto_speech_recognition,
            model='damo/speech_UniASR_asr_2pass-en-16k-common-vocab1080-tensorflow1-online')
        rec_result = inference_pipeline(
            audio_in='https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_en.wav',
            param_dict={"decoding_model":"normal"})
        logger.info("asr inference result: {0}".format(rec_result))

    def test_uniasr_2pass_es_common_offline(self):
        inference_pipeline = pipeline(
            task=Tasks.auto_speech_recognition,
            model='damo/speech_UniASR_asr_2pass-es-16k-common-vocab3445-tensorflow1-offline')
        rec_result = inference_pipeline(
            audio_in='https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_es.wav',
            param_dict={"decoding_model":"offline"})
        logger.info("asr inference result: {0}".format(rec_result))

    def test_uniasr_2pass_es_common_online(self):
        inference_pipeline = pipeline(
            task=Tasks.auto_speech_recognition,
            model='damo/speech_UniASR_asr_2pass-es-16k-common-vocab3445-tensorflow1-online')
        rec_result = inference_pipeline(
            audio_in='https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_es.wav',
            param_dict={"decoding_model":"normal"})
        logger.info("asr inference result: {0}".format(rec_result))

    def test_uniasr_2pass_fa_common_offline(self):
        inference_pipeline = pipeline(
            task=Tasks.auto_speech_recognition,
            model='damo/speech_UniASR_asr_2pass-fa-16k-common-vocab1257-pytorch-offline')
        rec_result = inference_pipeline(
            audio_in='https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_fa.wav',
            param_dict={"decoding_model":"offline"})
        logger.info("asr inference result: {0}".format(rec_result))

    def test_uniasr_2pass_fa_common_online(self):
        inference_pipeline = pipeline(
            task=Tasks.auto_speech_recognition,
            model='damo/speech_UniASR_asr_2pass-fa-16k-common-vocab1257-pytorch-online')
        rec_result = inference_pipeline(
            audio_in='https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_fa.wav',
            param_dict={"decoding_model":"normal"})
        logger.info("asr inference result: {0}".format(rec_result))

    def test_uniasr_2pass_fr_common_offline(self):
        inference_pipeline = pipeline(
            task=Tasks.auto_speech_recognition,
            model='damo/speech_UniASR_asr_2pass-fr-16k-common-vocab3472-tensorflow1-offline')
        rec_result = inference_pipeline(
            audio_in='https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_fr.wav',
            param_dict={"decoding_model":"offline"})
        logger.info("asr inference result: {0}".format(rec_result))

    def test_uniasr_2pass_fr_common_online(self):
        inference_pipeline = pipeline(
            task=Tasks.auto_speech_recognition,
            model='damo/speech_UniASR_asr_2pass-fr-16k-common-vocab3472-tensorflow1-online')
        rec_result = inference_pipeline(
            audio_in='https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_fr.wav',
            param_dict={"decoding_model":"normal"})
        logger.info("asr inference result: {0}".format(rec_result))
    
    def test_uniasr_2pass_id_common_offline(self):
        inference_pipeline = pipeline(
            task=Tasks.auto_speech_recognition,
            model='damo/speech_UniASR_asr_2pass-id-16k-common-vocab1067-tensorflow1-online')
        rec_result = inference_pipeline(
            audio_in='https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_id.wav',
            param_dict={"decoding_model":"offline"})
        logger.info("asr inference result: {0}".format(rec_result))

    def test_uniasr_2pass_id_common_online(self):
        inference_pipeline = pipeline(
            task=Tasks.auto_speech_recognition,
            model='damo/speech_UniASR_asr_2pass-id-16k-common-vocab1067-tensorflow1-online')
        rec_result = inference_pipeline(
            audio_in='https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_id.wav',
            param_dict={"decoding_model":"normal"})
        logger.info("asr inference result: {0}".format(rec_result))
        
    def test_uniasr_2pass_ja_common_offline(self):
        inference_pipeline = pipeline(
            task=Tasks.auto_speech_recognition,
            model='damo/speech_UniASR_asr_2pass-ja-16k-common-vocab93-tensorflow1-offline')
        rec_result = inference_pipeline(
            audio_in='https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_ja.wav',
            param_dict={"decoding_model":"offline"})
        logger.info("asr inference result: {0}".format(rec_result))

    def test_uniasr_2pass_ja_common_online(self):
        inference_pipeline = pipeline(
            task=Tasks.auto_speech_recognition,
            model='damo/speech_UniASR_asr_2pass-ja-16k-common-vocab93-tensorflow1-online')
        rec_result = inference_pipeline(
            audio_in='https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_ja.wav',
            param_dict={"decoding_model":"normal"})
        logger.info("asr inference result: {0}".format(rec_result))


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