docs

游雁

2023-04-27 c1d4bd297a4418ef44882079c4845cfe64ed0b21

docs

 egs_modelscope/asr/conformer/speech_conformer_asr_nat-zh-cn-16k-aishell1-vocab4234-pytorch/demo.py

@@ -4,11 +4,11 @@
if __name__ == '__main__':
    audio_in = 'https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav'
    output_dir = None
    inference_pipline = pipeline(
    inference_pipeline = pipeline(
        task=Tasks.auto_speech_recognition,
        model="damo/speech_conformer_asr_nat-zh-cn-16k-aishell1-vocab4234-pytorch",
        output_dir=output_dir,
    )
    rec_result = inference_pipline(audio_in=audio_in)
    rec_result = inference_pipeline(audio_in=audio_in)
    print(rec_result)


 egs_modelscope/asr/conformer/speech_conformer_asr_nat-zh-cn-16k-aishell2-vocab5212-pytorch/demo.py

@@ -4,10 +4,10 @@
if __name__ == "__main__":
    audio_in = "https://modelscope.oss-cn-beijing.aliyuncs.com/test/audios/asr_example.wav"
    output_dir = "./results"
    inference_pipline = pipeline(
    inference_pipeline = pipeline(
        task=Tasks.auto_speech_recognition,
        model="damo/speech_conformer_asr_nat-zh-cn-16k-aishell2-vocab5212-pytorch",
        output_dir=output_dir,
    )
    rec_result = inference_pipline(audio_in=audio_in)
    rec_result = inference_pipeline(audio_in=audio_in)
    print(rec_result)

 egs_modelscope/asr/data2vec/speech_data2vec_pretrain-paraformer-zh-cn-aishell2-16k/infer.py

@@ -16,13 +16,13 @@
        os.environ['CUDA_VISIBLE_DEVICES'] = str(gpu_list[gpu_id])
    else:
        os.environ['CUDA_VISIBLE_DEVICES'] = str(gpu_id)
    inference_pipline = pipeline(
    inference_pipeline = pipeline(
        task=Tasks.auto_speech_recognition,
        model="damo/speech_data2vec_pretrain-paraformer-zh-cn-aishell2-16k",
        output_dir=output_dir_job,
    )
    audio_in = os.path.join(split_dir, "wav.{}.scp".format(idx))
    inference_pipline(audio_in=audio_in)
    inference_pipeline(audio_in=audio_in)


def modelscope_infer(params):

 egs_modelscope/asr/data2vec/speech_data2vec_pretrain-zh-cn-aishell2-16k-pytorch/infer.py

@@ -16,13 +16,13 @@
        os.environ['CUDA_VISIBLE_DEVICES'] = str(gpu_list[gpu_id])
    else:
        os.environ['CUDA_VISIBLE_DEVICES'] = str(gpu_id)
    inference_pipline = pipeline(
    inference_pipeline = pipeline(
        task=Tasks.auto_speech_recognition,
        model="damo/speech_data2vec_pretrain-zh-cn-aishell2-16k-pytorch",
        output_dir=output_dir_job,
    )
    audio_in = os.path.join(split_dir, "wav.{}.scp".format(idx))
    inference_pipline(audio_in=audio_in)
    inference_pipeline(audio_in=audio_in)


def modelscope_infer(params):

 egs_modelscope/asr/paraformer/speech_paraformer-tiny-commandword_asr_nat-zh-cn-16k-vocab544-pytorch/infer.py

@@ -16,14 +16,14 @@
        os.environ['CUDA_VISIBLE_DEVICES'] = str(gpu_list[gpu_id])
    else:
        os.environ['CUDA_VISIBLE_DEVICES'] = str(gpu_id)
    inference_pipline = pipeline(
    inference_pipeline = pipeline(
        task=Tasks.auto_speech_recognition,
        model="damo/speech_paraformer-tiny-commandword_asr_nat-zh-cn-16k-vocab544-pytorch",
        output_dir=output_dir_job,
        batch_size=64
    )
    audio_in = os.path.join(split_dir, "wav.{}.scp".format(idx))
    inference_pipline(audio_in=audio_in)
    inference_pipeline(audio_in=audio_in)


def modelscope_infer(params):

 egs_modelscope/asr/paraformer/speech_paraformer_asr_nat-zh-cn-16k-aishell1-vocab4234-pytorch/demo.py

@@ -4,12 +4,12 @@
if __name__ == '__main__':
    audio_in = 'https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav'
    output_dir = None
    inference_pipline = pipeline(
    inference_pipeline = pipeline(
        task=Tasks.auto_speech_recognition,
        model="damo/speech_paraformer_asr_nat-zh-cn-16k-aishell1-vocab4234-pytorch",
        output_dir=output_dir,
        batch_size=1,
    )
    rec_result = inference_pipline(audio_in=audio_in)
    rec_result = inference_pipeline(audio_in=audio_in)
    print(rec_result)


 egs_modelscope/asr/paraformer/speech_paraformer_asr_nat-zh-cn-16k-aishell2-vocab5212-pytorch/demo.py

@@ -4,10 +4,10 @@
if __name__ == "__main__":
    audio_in = "https://modelscope.oss-cn-beijing.aliyuncs.com/test/audios/asr_example.wav"
    output_dir = "./results"
    inference_pipline = pipeline(
    inference_pipeline = pipeline(
        task=Tasks.auto_speech_recognition,
        model="damo/speech_paraformer_asr_nat-zh-cn-16k-aishell2-vocab5212-pytorch",
        output_dir=output_dir,
    )
    rec_result = inference_pipline(audio_in=audio_in)
    rec_result = inference_pipeline(audio_in=audio_in)
    print(rec_result)

 egs_modelscope/asr/paraformerbert/speech_paraformerbert_asr_nat-zh-cn-16k-aishell1-vocab4234-pytorch/infer.py

@@ -4,11 +4,11 @@
if __name__ == '__main__':
    audio_in = 'https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav'
    output_dir = None
    inference_pipline = pipeline(
    inference_pipeline = pipeline(
        task=Tasks.auto_speech_recognition,
        model="damo/speech_paraformerbert_asr_nat-zh-cn-16k-aishell1-vocab4234-pytorch",
        output_dir=output_dir,
    )
    rec_result = inference_pipline(audio_in=audio_in)
    rec_result = inference_pipeline(audio_in=audio_in)
    print(rec_result)


 egs_modelscope/asr/paraformerbert/speech_paraformerbert_asr_nat-zh-cn-16k-aishell2-vocab5212-pytorch/infer.py

@@ -4,10 +4,10 @@
if __name__ == "__main__":
    audio_in = "https://modelscope.oss-cn-beijing.aliyuncs.com/test/audios/asr_example.wav"
    output_dir = "./results"
    inference_pipline = pipeline(
    inference_pipeline = pipeline(
        task=Tasks.auto_speech_recognition,
        model="damo/speech_paraformerbert_asr_nat-zh-cn-16k-aishell2-vocab5212-pytorch",
        output_dir=output_dir,
    )
    rec_result = inference_pipline(audio_in=audio_in)
    rec_result = inference_pipeline(audio_in=audio_in)
    print(rec_result)

 egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-cantonese-CHS-16k-common-vocab1468-tensorflow1-offline/infer.py

@@ -4,10 +4,10 @@
if __name__ == "__main__":
    audio_in = "https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_cantonese-CHS.wav"
    output_dir = "./results"
    inference_pipline = pipeline(
    inference_pipeline = pipeline(
        task=Tasks.auto_speech_recognition,
        model="damo/speech_UniASR_asr_2pass-cantonese-CHS-16k-common-vocab1468-tensorflow1-online",
        output_dir=output_dir,
    )
    rec_result = inference_pipline(audio_in=audio_in, param_dict={"decoding_model":"offline"})
    rec_result = inference_pipeline(audio_in=audio_in, param_dict={"decoding_model":"offline"})
    print(rec_result)

 egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-cantonese-CHS-16k-common-vocab1468-tensorflow1-online/infer.py

@@ -4,10 +4,10 @@
if __name__ == "__main__":
    audio_in = "https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_cantonese-CHS.wav"
    output_dir = "./results"
    inference_pipline = pipeline(
    inference_pipeline = pipeline(
        task=Tasks.auto_speech_recognition,
        model="damo/speech_UniASR_asr_2pass-cantonese-CHS-16k-common-vocab1468-tensorflow1-online",
        output_dir=output_dir,
    )
    rec_result = inference_pipline(audio_in=audio_in, param_dict={"decoding_model":"normal"})
    rec_result = inference_pipeline(audio_in=audio_in, param_dict={"decoding_model":"normal"})
    print(rec_result)

 egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-cn-dialect-16k-vocab8358-tensorflow1-offline/infer.py

@@ -4,11 +4,11 @@
if __name__ == '__main__':
    audio_in = 'https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav'
    output_dir = None
    inference_pipline = pipeline(
    inference_pipeline = pipeline(
        task=Tasks.auto_speech_recognition,
        model="damo/speech_UniASR_asr_2pass-cn-dialect-16k-vocab8358-tensorflow1-offline",
        output_dir=output_dir,
    )
    rec_result = inference_pipline(audio_in=audio_in)
    rec_result = inference_pipeline(audio_in=audio_in)
    print(rec_result)


 egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-cn-dialect-16k-vocab8358-tensorflow1-online/infer.py

@@ -4,11 +4,11 @@
if __name__ == '__main__':
    audio_in = 'https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav'
    output_dir = None
    inference_pipline = pipeline(
    inference_pipeline = pipeline(
        task=Tasks.auto_speech_recognition,
        model="damo/speech_UniASR_asr_2pass-cn-dialect-16k-vocab8358-tensorflow1-online",
        output_dir=output_dir,
    )
    rec_result = inference_pipline(audio_in=audio_in)
    rec_result = inference_pipeline(audio_in=audio_in)
    print(rec_result)


 egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-de-16k-common-vocab3690-tensorflow1-offline/infer.py

@@ -4,10 +4,10 @@
if __name__ == "__main__":
    audio_in = "https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_de.wav"
    output_dir = "./results"
    inference_pipline = pipeline(
    inference_pipeline = pipeline(
        task=Tasks.auto_speech_recognition,
        model="damo/speech_UniASR_asr_2pass-de-16k-common-vocab3690-tensorflow1-offline",
        output_dir=output_dir,
    )
    rec_result = inference_pipline(audio_in=audio_in, param_dict={"decoding_model":"offline"})
    rec_result = inference_pipeline(audio_in=audio_in, param_dict={"decoding_model":"offline"})
    print(rec_result)

 egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-de-16k-common-vocab3690-tensorflow1-online/infer.py

@@ -4,10 +4,10 @@
if __name__ == "__main__":
    audio_in = "https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_de.wav"
    output_dir = "./results"
    inference_pipline = pipeline(
    inference_pipeline = pipeline(
        task=Tasks.auto_speech_recognition,
        model="damo/speech_UniASR_asr_2pass-de-16k-common-vocab3690-tensorflow1-online",
        output_dir=output_dir,
    )
    rec_result = inference_pipline(audio_in=audio_in, param_dict={"decoding_model":"normal"})
    rec_result = inference_pipeline(audio_in=audio_in, param_dict={"decoding_model":"normal"})
    print(rec_result)

 egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-en-16k-common-vocab1080-tensorflow1-offline/infer.py

@@ -4,10 +4,10 @@
if __name__ == "__main__":
    audio_in = "https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_en.wav"
    output_dir = "./results"
    inference_pipline = pipeline(
    inference_pipeline = pipeline(
        task=Tasks.auto_speech_recognition,
        model="damo/speech_UniASR_asr_2pass-en-16k-common-vocab1080-tensorflow1-offline",
        output_dir=output_dir,
    )
    rec_result = inference_pipline(audio_in=audio_in, param_dict={"decoding_model":"offline"})
    rec_result = inference_pipeline(audio_in=audio_in, param_dict={"decoding_model":"offline"})
    print(rec_result)

 egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-en-16k-common-vocab1080-tensorflow1-online/infer.py

@@ -4,10 +4,10 @@
if __name__ == "__main__":
    audio_in = "https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_en.wav"
    output_dir = "./results"
    inference_pipline = pipeline(
    inference_pipeline = pipeline(
        task=Tasks.auto_speech_recognition,
        model="damo/speech_UniASR_asr_2pass-en-16k-common-vocab1080-tensorflow1-online",
        output_dir=output_dir,
    )
    rec_result = inference_pipline(audio_in=audio_in, param_dict={"decoding_model":"normal"})
    rec_result = inference_pipeline(audio_in=audio_in, param_dict={"decoding_model":"normal"})
    print(rec_result)

 egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-es-16k-common-vocab3445-tensorflow1-offline/infer.py

@@ -4,10 +4,10 @@
if __name__ == "__main__":
    audio_in = "https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_es.wav"
    output_dir = "./results"
    inference_pipline = pipeline(
    inference_pipeline = pipeline(
        task=Tasks.auto_speech_recognition,
        model="damo/speech_UniASR_asr_2pass-es-16k-common-vocab3445-tensorflow1-offline",
        output_dir=output_dir,
    )
    rec_result = inference_pipline(audio_in=audio_in, param_dict={"decoding_model":"offline"})
    rec_result = inference_pipeline(audio_in=audio_in, param_dict={"decoding_model":"offline"})
    print(rec_result)

 egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-es-16k-common-vocab3445-tensorflow1-online/infer.py

@@ -4,10 +4,10 @@
if __name__ == "__main__":
    audio_in = "https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_es.wav"
    output_dir = "./results"
    inference_pipline = pipeline(
    inference_pipeline = pipeline(
        task=Tasks.auto_speech_recognition,
        model="damo/speech_UniASR_asr_2pass-es-16k-common-vocab3445-tensorflow1-online",
        output_dir=output_dir,
    )
    rec_result = inference_pipline(audio_in=audio_in, param_dict={"decoding_model":"normal"})
    rec_result = inference_pipeline(audio_in=audio_in, param_dict={"decoding_model":"normal"})
    print(rec_result)

 egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-fa-16k-common-vocab1257-pytorch-offline/infer.py

@@ -16,14 +16,14 @@
        os.environ['CUDA_VISIBLE_DEVICES'] = str(gpu_list[gpu_id])
    else:
        os.environ['CUDA_VISIBLE_DEVICES'] = str(gpu_id)
    inference_pipline = pipeline(
    inference_pipeline = pipeline(
        task=Tasks.auto_speech_recognition,
        model="damo/speech_UniASR_asr_2pass-fa-16k-common-vocab1257-pytorch-offline",
        output_dir=output_dir_job,
        batch_size=1
    )
    audio_in = os.path.join(split_dir, "wav.{}.scp".format(idx))
    inference_pipline(audio_in=audio_in, param_dict={"decoding_model":"offline"})
    inference_pipeline(audio_in=audio_in, param_dict={"decoding_model":"offline"})


def modelscope_infer(params):

 egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-fa-16k-common-vocab1257-pytorch-online/infer.py

@@ -16,14 +16,14 @@
        os.environ['CUDA_VISIBLE_DEVICES'] = str(gpu_list[gpu_id])
    else:
        os.environ['CUDA_VISIBLE_DEVICES'] = str(gpu_id)
    inference_pipline = pipeline(
    inference_pipeline = pipeline(
        task=Tasks.auto_speech_recognition,
        model="damo/speech_UniASR_asr_2pass-fa-16k-common-vocab1257-pytorch-online",
        output_dir=output_dir_job,
        batch_size=1
    )
    audio_in = os.path.join(split_dir, "wav.{}.scp".format(idx))
    inference_pipline(audio_in=audio_in, param_dict={"decoding_model":"normal"})
    inference_pipeline(audio_in=audio_in, param_dict={"decoding_model":"normal"})


def modelscope_infer(params):

 egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-fr-16k-common-vocab3472-tensorflow1-offline/infer.py

@@ -4,10 +4,10 @@
if __name__ == "__main__":
    audio_in = "https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_fr.wav"
    output_dir = "./results"
    inference_pipline = pipeline(
    inference_pipeline = pipeline(
        task=Tasks.auto_speech_recognition,
        model="damo/speech_UniASR_asr_2pass-fr-16k-common-vocab3472-tensorflow1-offline",
        output_dir=output_dir,
    )
    rec_result = inference_pipline(audio_in=audio_in, param_dict={"decoding_model":"offline"})
    rec_result = inference_pipeline(audio_in=audio_in, param_dict={"decoding_model":"offline"})
    print(rec_result)

 egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-fr-16k-common-vocab3472-tensorflow1-online/infer.py

@@ -4,10 +4,10 @@
if __name__ == "__main__":
    audio_in = "https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_fr.wav"
    output_dir = "./results"
    inference_pipline = pipeline(
    inference_pipeline = pipeline(
        task=Tasks.auto_speech_recognition,
        model="damo/speech_UniASR_asr_2pass-fr-16k-common-vocab3472-tensorflow1-online",
        output_dir=output_dir,
    )
    rec_result = inference_pipline(audio_in=audio_in, param_dict={"decoding_model":"normal"})
    rec_result = inference_pipeline(audio_in=audio_in, param_dict={"decoding_model":"normal"})
    print(rec_result)

 egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-he-16k-common-vocab1085-pytorch/infer.py

@@ -4,10 +4,10 @@
if __name__ == "__main__":
    audio_in = "https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_he.wav"
    output_dir = "./results"
    inference_pipline = pipeline(
    inference_pipeline = pipeline(
        task=Tasks.auto_speech_recognition,
        model="damo/speech_UniASR_asr_2pass-he-16k-common-vocab1085-pytorch",
        output_dir=output_dir,
    )
    rec_result = inference_pipline(audio_in=audio_in, param_dict={"decoding_model":"offline"})
    rec_result = inference_pipeline(audio_in=audio_in, param_dict={"decoding_model":"offline"})
    print(rec_result)

 egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-id-16k-common-vocab1067-tensorflow1-offline/infer.py

@@ -4,10 +4,10 @@
if __name__ == "__main__":
    audio_in = "https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_id.wav"
    output_dir = "./results"
    inference_pipline = pipeline(
    inference_pipeline = pipeline(
        task=Tasks.auto_speech_recognition,
        model="damo/speech_UniASR_asr_2pass-id-16k-common-vocab1067-tensorflow1-online",
        output_dir=output_dir,
    )
    rec_result = inference_pipline(audio_in=audio_in, param_dict={"decoding_model":"offline"})
    rec_result = inference_pipeline(audio_in=audio_in, param_dict={"decoding_model":"offline"})
    print(rec_result)

 egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-id-16k-common-vocab1067-tensorflow1-online/infer.py

@@ -4,10 +4,10 @@
if __name__ == "__main__":
    audio_in = "https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_id.wav"
    output_dir = "./results"
    inference_pipline = pipeline(
    inference_pipeline = pipeline(
        task=Tasks.auto_speech_recognition,
        model="damo/speech_UniASR_asr_2pass-id-16k-common-vocab1067-tensorflow1-online",
        output_dir=output_dir,
    )
    rec_result = inference_pipline(audio_in=audio_in, param_dict={"decoding_model":"normal"})
    rec_result = inference_pipeline(audio_in=audio_in, param_dict={"decoding_model":"normal"})
    print(rec_result)

 egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-ja-16k-common-vocab93-tensorflow1-offline/infer.py

@@ -4,10 +4,10 @@
if __name__ == "__main__":
    audio_in = "https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_ja.wav"
    output_dir = "./results"
    inference_pipline = pipeline(
    inference_pipeline = pipeline(
        task=Tasks.auto_speech_recognition,
        model="damo/speech_UniASR_asr_2pass-ja-16k-common-vocab93-tensorflow1-offline",
        output_dir=output_dir,
    )
    rec_result = inference_pipline(audio_in=audio_in, param_dict={"decoding_model":"offline"})
    rec_result = inference_pipeline(audio_in=audio_in, param_dict={"decoding_model":"offline"})
    print(rec_result)

 egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-ja-16k-common-vocab93-tensorflow1-online/infer.py

@@ -4,10 +4,10 @@
if __name__ == "__main__":
    audio_in = "https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_ja.wav"
    output_dir = "./results"
    inference_pipline = pipeline(
    inference_pipeline = pipeline(
        task=Tasks.auto_speech_recognition,
        model="damo/speech_UniASR_asr_2pass-ja-16k-common-vocab93-tensorflow1-online",
        output_dir=output_dir,
    )
    rec_result = inference_pipline(audio_in=audio_in, param_dict={"decoding_model":"normal"})
    rec_result = inference_pipeline(audio_in=audio_in, param_dict={"decoding_model":"normal"})
    print(rec_result)

 egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-ko-16k-common-vocab6400-tensorflow1-offline/infer.py

@@ -4,10 +4,10 @@
if __name__ == "__main__":
    audio_in = "https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_ko.wav"
    output_dir = "./results"
    inference_pipline = pipeline(
    inference_pipeline = pipeline(
        task=Tasks.auto_speech_recognition,
        model="damo/speech_UniASR_asr_2pass-ko-16k-common-vocab6400-tensorflow1-offline",
        output_dir=output_dir,
    )
    rec_result = inference_pipline(audio_in=audio_in, param_dict={"decoding_model":"offline"})
    rec_result = inference_pipeline(audio_in=audio_in, param_dict={"decoding_model":"offline"})
    print(rec_result)

 egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-ko-16k-common-vocab6400-tensorflow1-online/infer.py

@@ -4,10 +4,10 @@
if __name__ == "__main__":
    audio_in = "https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_ko.wav"
    output_dir = "./results"
    inference_pipline = pipeline(
    inference_pipeline = pipeline(
        task=Tasks.auto_speech_recognition,
        model="damo/speech_UniASR_asr_2pass-ko-16k-common-vocab6400-tensorflow1-online",
        output_dir=output_dir,
    )
    rec_result = inference_pipline(audio_in=audio_in, param_dict={"decoding_model":"normal"})
    rec_result = inference_pipeline(audio_in=audio_in, param_dict={"decoding_model":"normal"})
    print(rec_result)

 egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-my-16k-common-vocab696-pytorch/infer.py

@@ -4,10 +4,10 @@
if __name__ == "__main__":
    audio_in = "https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_my.wav"
    output_dir = "./results"
    inference_pipline = pipeline(
    inference_pipeline = pipeline(
        task=Tasks.auto_speech_recognition,
        model="damo/speech_UniASR_asr_2pass-my-16k-common-vocab696-pytorch",
        output_dir=output_dir,
    )
    rec_result = inference_pipline(audio_in=audio_in, param_dict={"decoding_model":"offline"})
    rec_result = inference_pipeline(audio_in=audio_in, param_dict={"decoding_model":"offline"})
    print(rec_result)

 egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-pt-16k-common-vocab1617-tensorflow1-offline/infer.py

@@ -4,10 +4,10 @@
if __name__ == "__main__":
    audio_in = "https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_pt.wav"
    output_dir = "./results"
    inference_pipline = pipeline(
    inference_pipeline = pipeline(
        task=Tasks.auto_speech_recognition,
        model="damo/speech_UniASR_asr_2pass-pt-16k-common-vocab1617-tensorflow1-offline",
        output_dir=output_dir,
    )
    rec_result = inference_pipline(audio_in=audio_in, param_dict={"decoding_model":"offline"})
    rec_result = inference_pipeline(audio_in=audio_in, param_dict={"decoding_model":"offline"})
    print(rec_result)

 egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-pt-16k-common-vocab1617-tensorflow1-online/infer.py

@@ -4,10 +4,10 @@
if __name__ == "__main__":
    audio_in = "https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_pt.wav"
    output_dir = "./results"
    inference_pipline = pipeline(
    inference_pipeline = pipeline(
        task=Tasks.auto_speech_recognition,
        model="damo/speech_UniASR_asr_2pass-pt-16k-common-vocab1617-tensorflow1-online",
        output_dir=output_dir,
    )
    rec_result = inference_pipline(audio_in=audio_in, param_dict={"decoding_model":"normal"})
    rec_result = inference_pipeline(audio_in=audio_in, param_dict={"decoding_model":"normal"})
    print(rec_result)

 egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-ru-16k-common-vocab1664-tensorflow1-offline/infer.py

@@ -4,10 +4,10 @@
if __name__ == "__main__":
    audio_in = "https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_ru.wav"
    output_dir = "./results"
    inference_pipline = pipeline(
    inference_pipeline = pipeline(
        task=Tasks.auto_speech_recognition,
        model="damo/speech_UniASR_asr_2pass-ru-16k-common-vocab1664-tensorflow1-offline",
        output_dir=output_dir,
    )
    rec_result = inference_pipline(audio_in=audio_in, param_dict={"decoding_model":"offline"})
    rec_result = inference_pipeline(audio_in=audio_in, param_dict={"decoding_model":"offline"})
    print(rec_result)

 egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-ru-16k-common-vocab1664-tensorflow1-online/infer.py

@@ -4,10 +4,10 @@
if __name__ == "__main__":
    audio_in = "https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_ru.wav"
    output_dir = "./results"
    inference_pipline = pipeline(
    inference_pipeline = pipeline(
        task=Tasks.auto_speech_recognition,
        model="damo/speech_UniASR_asr_2pass-ru-16k-common-vocab1664-tensorflow1-online",
        output_dir=output_dir,
    )
    rec_result = inference_pipline(audio_in=audio_in, param_dict={"decoding_model":"normal"})
    rec_result = inference_pipeline(audio_in=audio_in, param_dict={"decoding_model":"normal"})
    print(rec_result)

 egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-ur-16k-common-vocab877-pytorch/infer.py

@@ -4,10 +4,10 @@
if __name__ == "__main__":
    audio_in = "https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_ur.wav"
    output_dir = "./results"
    inference_pipline = pipeline(
    inference_pipeline = pipeline(
        task=Tasks.auto_speech_recognition,
        model="damo/speech_UniASR_asr_2pass-ur-16k-common-vocab877-pytorch",
        output_dir=output_dir,
    )
    rec_result = inference_pipline(audio_in=audio_in, param_dict={"decoding_model":"offline"})
    rec_result = inference_pipeline(audio_in=audio_in, param_dict={"decoding_model":"offline"})
    print(rec_result)

 egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-vi-16k-common-vocab1001-pytorch-offline/infer.py

@@ -4,10 +4,10 @@
if __name__ == "__main__":
    audio_in = "https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_vi.wav"
    output_dir = "./results"
    inference_pipline = pipeline(
    inference_pipeline = pipeline(
        task=Tasks.auto_speech_recognition,
        model="damo/speech_UniASR_asr_2pass-vi-16k-common-vocab1001-pytorch-offline",
        output_dir=output_dir,
    )
    rec_result = inference_pipline(audio_in=audio_in, param_dict={"decoding_model":"offline"})
    rec_result = inference_pipeline(audio_in=audio_in, param_dict={"decoding_model":"offline"})
    print(rec_result)

 egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-vi-16k-common-vocab1001-pytorch-online/infer.py

@@ -4,10 +4,10 @@
if __name__ == "__main__":
    audio_in = "https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_vi.wav"
    output_dir = "./results"
    inference_pipline = pipeline(
    inference_pipeline = pipeline(
        task=Tasks.auto_speech_recognition,
        model="damo/speech_UniASR_asr_2pass-vi-16k-common-vocab1001-pytorch-online",
        output_dir=output_dir,
    )
    rec_result = inference_pipline(audio_in=audio_in, param_dict={"decoding_model":"normal"})
    rec_result = inference_pipeline(audio_in=audio_in, param_dict={"decoding_model":"normal"})
    print(rec_result)

 egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-zh-cn-16k-common-vocab8358-tensorflow1-offline/infer.py

@@ -4,11 +4,11 @@
if __name__ == '__main__':
    audio_in = 'https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav'
    output_dir = None
    inference_pipline = pipeline(
    inference_pipeline = pipeline(
        task=Tasks.auto_speech_recognition,
        model="damo/speech_UniASR_asr_2pass-zh-cn-16k-common-vocab8358-tensorflow1-offline",
        output_dir=output_dir,
    )
    rec_result = inference_pipline(audio_in=audio_in)
    rec_result = inference_pipeline(audio_in=audio_in)
    print(rec_result)


 egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-zh-cn-16k-common-vocab8358-tensorflow1-online/infer.py

@@ -4,11 +4,11 @@
if __name__ == '__main__':
    audio_in = 'https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav'
    output_dir = None
    inference_pipline = pipeline(
    inference_pipeline = pipeline(
        task=Tasks.auto_speech_recognition,
        model="damo/speech_UniASR_asr_2pass-zh-cn-16k-common-vocab8358-tensorflow1-online",
        output_dir=output_dir,
    )
    rec_result = inference_pipline(audio_in=audio_in)
    rec_result = inference_pipeline(audio_in=audio_in)
    print(rec_result)


 egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab3445-pytorch-offline/infer.py

@@ -16,14 +16,14 @@
        os.environ['CUDA_VISIBLE_DEVICES'] = str(gpu_list[gpu_id])
    else:
        os.environ['CUDA_VISIBLE_DEVICES'] = str(gpu_id)
    inference_pipline = pipeline(
    inference_pipeline = pipeline(
        task=Tasks.auto_speech_recognition,
        model="damo/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab3445-pytorch-offline",
        output_dir=output_dir_job,
        batch_size=1
    )
    audio_in = os.path.join(split_dir, "wav.{}.scp".format(idx))
    inference_pipline(audio_in=audio_in)
    inference_pipeline(audio_in=audio_in)

def modelscope_infer(params):
    # prepare for multi-GPU decoding

 egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab3445-pytorch-online/infer.py

@@ -16,14 +16,14 @@
        os.environ['CUDA_VISIBLE_DEVICES'] = str(gpu_list[gpu_id])
    else:
        os.environ['CUDA_VISIBLE_DEVICES'] = str(gpu_id)
    inference_pipline = pipeline(
    inference_pipeline = pipeline(
        task=Tasks.auto_speech_recognition,
        model="damo/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab3445-pytorch-online",
        output_dir=output_dir_job,
        batch_size=1
    )
    audio_in = os.path.join(split_dir, "wav.{}.scp".format(idx))
    inference_pipline(audio_in=audio_in, param_dict={"decoding_model": "normal"})
    inference_pipeline(audio_in=audio_in, param_dict={"decoding_model": "normal"})


def modelscope_infer(params):

 egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab8358-tensorflow1-offline/infer.py

@@ -4,11 +4,11 @@
if __name__ == '__main__':
    audio_in = 'https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav'
    output_dir = None
    inference_pipline = pipeline(
    inference_pipeline = pipeline(
        task=Tasks.auto_speech_recognition,
        model="damo/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab8358-tensorflow1-offline",
        output_dir=output_dir,
    )
    rec_result = inference_pipline(audio_in=audio_in)
    rec_result = inference_pipeline(audio_in=audio_in)
    print(rec_result)


 egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab8358-tensorflow1-online/infer.py

@@ -4,11 +4,11 @@
if __name__ == '__main__':
    audio_in = 'https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav'
    output_dir = None
    inference_pipline = pipeline(
    inference_pipeline = pipeline(
        task=Tasks.auto_speech_recognition,
        model="damo/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab8358-tensorflow1-online",
        output_dir=output_dir,
    )
    rec_result = inference_pipline(audio_in=audio_in)
    rec_result = inference_pipeline(audio_in=audio_in)
    print(rec_result)


 egs_modelscope/lm/speech_transformer_lm_zh-cn-common-vocab8404-pytorch/infer.py

@@ -6,12 +6,12 @@
from modelscope.pipelines import pipeline
from modelscope.utils.constant import Tasks

inference_pipline = pipeline(
inference_pipeline = pipeline(
    task=Tasks.language_score_prediction,
    model='damo/speech_transformer_lm_zh-cn-common-vocab8404-pytorch',
    output_dir="./tmp/"
)

rec_result = inference_pipline(text_in=inputs)
rec_result = inference_pipeline(text_in=inputs)
print(rec_result)


 egs_modelscope/punctuation/TEMPLATE/README.md

@@ -11,21 +11,21 @@
from modelscope.pipelines import pipeline
from modelscope.utils.constant import Tasks

inference_pipline = pipeline(
inference_pipeline = pipeline(
    task=Tasks.punctuation,
    model='damo/punc_ct-transformer_zh-cn-common-vocab272727-pytorch',
    model_revision=None)

rec_result = inference_pipline(text_in='example/punc_example.txt')
rec_result = inference_pipeline(text_in='example/punc_example.txt')
print(rec_result)
```
- text二进制数据，例如：用户直接从文件里读出bytes数据
```python
rec_result = inference_pipline(text_in='我们都是木头人不会讲话不会动')
rec_result = inference_pipeline(text_in='我们都是木头人不会讲话不会动')
```
- text文件url，例如：https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_text/punc_example.txt
```python
rec_result = inference_pipline(text_in='https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_text/punc_example.txt')
rec_result = inference_pipeline(text_in='https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_text/punc_example.txt')
```

#### [CT-Transformer Realtime model](https://www.modelscope.cn/models/damo/punc_ct-transformer_zh-cn-common-vad_realtime-vocab272727/summary)

 egs_modelscope/punctuation/punc_ct-transformer_zh-cn-common-vocab272727-pytorch/demo.py

@@ -12,12 +12,12 @@
from modelscope.pipelines import pipeline
from modelscope.utils.constant import Tasks

inference_pipline = pipeline(
inference_pipeline = pipeline(
    task=Tasks.punctuation,
    model='damo/punc_ct-transformer_zh-cn-common-vocab272727-pytorch',
    model_revision="v1.1.7",
    output_dir="./tmp/"
)

rec_result = inference_pipline(text_in=inputs)
rec_result = inference_pipeline(text_in=inputs)
print(rec_result)

 egs_modelscope/tp/TEMPLATE/README.md

@@ -8,12 +8,12 @@
from modelscope.pipelines import pipeline
from modelscope.utils.constant import Tasks

inference_pipline = pipeline(
inference_pipeline = pipeline(
    task=Tasks.speech_timestamp,
    model='damo/speech_timestamp_prediction-v1-16k-offline',
    output_dir=None)

rec_result = inference_pipline(
rec_result = inference_pipeline(
    audio_in='https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_timestamps.wav',
    text_in='一 个 东 太 平 洋 国 家 为 什 么 跑 到 西 太 平 洋 来 了 呢',)
print(rec_result)

 egs_modelscope/tp/speech_timestamp_prediction-v1-16k-offline/demo.py

@@ -1,12 +1,12 @@
from modelscope.pipelines import pipeline
from modelscope.utils.constant import Tasks

inference_pipline = pipeline(
inference_pipeline = pipeline(
    task=Tasks.speech_timestamp,
    model='damo/speech_timestamp_prediction-v1-16k-offline',
    output_dir=None)

rec_result = inference_pipline(
rec_result = inference_pipeline(
    audio_in='https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_timestamps.wav',
    text_in='一 个 东 太 平 洋 国 家 为 什 么 跑 到 西 太 平 洋 来 了 呢',)
print(rec_result)

 egs_modelscope/vad/speech_fsmn_vad_zh-cn-16k-common/demo.py

@@ -4,12 +4,12 @@
if __name__ == '__main__':
    audio_in = 'https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/vad_example.wav'
    output_dir = None
    inference_pipline = pipeline(
    inference_pipeline = pipeline(
        task=Tasks.voice_activity_detection,
        model="damo/speech_fsmn_vad_zh-cn-16k-common-pytorch",
        model_revision='v1.2.0',
        output_dir=output_dir,
        batch_size=1,
    )
    segments_result = inference_pipline(audio_in=audio_in)
    segments_result = inference_pipeline(audio_in=audio_in)
    print(segments_result)

 egs_modelscope/vad/speech_fsmn_vad_zh-cn-16k-common/demo_online.py

@@ -8,7 +8,7 @@

if __name__ == '__main__':
    output_dir = None
    inference_pipline = pipeline(
    inference_pipeline = pipeline(
        task=Tasks.voice_activity_detection,
        model="damo/speech_fsmn_vad_zh-cn-16k-common-pytorch",
        model_revision='v1.2.0',
@@ -30,7 +30,7 @@
        else:
            is_final = False
        param_dict['is_final'] = is_final
        segments_result = inference_pipline(audio_in=speech[sample_offset: sample_offset + step],
        segments_result = inference_pipeline(audio_in=speech[sample_offset: sample_offset + step],
                                            param_dict=param_dict)
        print(segments_result)


 egs_modelscope/vad/speech_fsmn_vad_zh-cn-8k-common/demo.py

@@ -4,12 +4,12 @@
if __name__ == '__main__':
    audio_in = 'https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/vad_example_8k.wav'
    output_dir = None
    inference_pipline = pipeline(
    inference_pipeline = pipeline(
        task=Tasks.voice_activity_detection,
        model="damo/speech_fsmn_vad_zh-cn-8k-common",
        model_revision='v1.2.0',
        output_dir=output_dir,
        batch_size=1,
    )
    segments_result = inference_pipline(audio_in=audio_in)
    segments_result = inference_pipeline(audio_in=audio_in)
    print(segments_result)

 egs_modelscope/vad/speech_fsmn_vad_zh-cn-8k-common/demo_online.py

@@ -8,7 +8,7 @@

if __name__ == '__main__':
    output_dir = None
    inference_pipline = pipeline(
    inference_pipeline = pipeline(
        task=Tasks.voice_activity_detection,
        model="damo/speech_fsmn_vad_zh-cn-8k-common",
        model_revision='v1.2.0',
@@ -30,7 +30,7 @@
        else:
            is_final = False
        param_dict['is_final'] = is_final
        segments_result = inference_pipline(audio_in=speech[sample_offset: sample_offset + step],
        segments_result = inference_pipeline(audio_in=speech[sample_offset: sample_offset + step],
                                            param_dict=param_dict)
        print(segments_result)