PaddleSpeech/demos/speech_server/conf/application.yaml

# This is the parameter configuration file for PaddleSpeech Offline Serving.

#################################################################################
#                             SERVER SETTING                                    #
#################################################################################
host: 0.0.0.0
port: 8090

# The task format in the engin_list is: <speech task>_<engine type>
# task choices = ['asr_python', 'asr_inference', 'tts_python', 'tts_inference', 'cls_python', 'cls_inference', 'text_python', 'vector_python']
protocol: 'http'
engine_list: ['asr_python', 'tts_python', 'cls_python', 'text_python', 'vector_python']


#################################################################################
#                                ENGINE CONFIG                                  #
#################################################################################

################################### ASR #########################################
################### speech task: asr; engine_type: python #######################
asr_python:
    model: 'conformer_wenetspeech'
    lang: 'zh'
    sample_rate: 16000
    cfg_path: # [optional]
    ckpt_path: # [optional]
    decode_method: 'attention_rescoring'
    force_yes: True
    device:  # set 'gpu:id' or 'cpu'

################### speech task: asr; engine_type: inference #######################
asr_inference:
    # model_type choices=['deepspeech2offline_aishell']
    model_type: 'deepspeech2offline_aishell'
    am_model: # the pdmodel file of am static model [optional]
    am_params:  # the pdiparams file of am static model [optional]
    lang: 'zh'
    sample_rate: 16000
    cfg_path: 
    decode_method: 
    force_yes: True

    am_predictor_conf:
        device:  # set 'gpu:id' or 'cpu'
        switch_ir_optim: True
        glog_info: False  # True -> print glog
        summary: True  # False -> do not show predictor config


################################### TTS #########################################
################### speech task: tts; engine_type: python #######################
tts_python:
    # am (acoustic model) choices=['speedyspeech_csmsc', 'fastspeech2_csmsc',
    #                             'fastspeech2_ljspeech', 'fastspeech2_aishell3',
    #                             'fastspeech2_vctk', 'fastspeech2_mix',
    #                             'tacotron2_csmsc', 'tacotron2_ljspeech']
    am: 'fastspeech2_csmsc'   
    am_config: 
    am_ckpt: 
    am_stat: 
    phones_dict: 
    tones_dict: 
    speaker_dict: 


    # voc (vocoder) choices=['pwgan_csmsc', 'pwgan_ljspeech', 'pwgan_aishell3',
    #                        'pwgan_vctk', 'mb_melgan_csmsc', 'style_melgan_csmsc',
    #                        'hifigan_csmsc', 'hifigan_ljspeech', 'hifigan_aishell3',
    #                        'hifigan_vctk', 'wavernn_csmsc']
    voc: 'mb_melgan_csmsc'
    voc_config: 
    voc_ckpt: 
    voc_stat: 

    # others
    lang: 'zh'
    device:  # set 'gpu:id' or 'cpu'


################### speech task: tts; engine_type: inference #######################
tts_inference:
    # am (acoustic model) choices=['speedyspeech_csmsc', 'fastspeech2_csmsc']
    am: 'fastspeech2_csmsc'   
    am_model: # the pdmodel file of your am static model (XX.pdmodel)
    am_params: # the pdiparams file of your am static model (XX.pdipparams)
    am_sample_rate: 24000
    phones_dict: 
    tones_dict: 
    speaker_dict: 


    am_predictor_conf:
        device:  # set 'gpu:id' or 'cpu'
        switch_ir_optim: True
        glog_info: False # True -> print glog
        summary: True  # False -> do not show predictor config

    # voc (vocoder) choices=['pwgan_csmsc', 'mb_melgan_csmsc','hifigan_csmsc']
    voc: 'mb_melgan_csmsc'
    voc_model: # the pdmodel file of your vocoder static model (XX.pdmodel)
    voc_params: # the pdiparams file of your vocoder static model (XX.pdipparams)
    voc_sample_rate: 24000

    voc_predictor_conf:
        device:  # set 'gpu:id' or 'cpu'  
        switch_ir_optim: True  
        glog_info: False # True -> print glog
        summary: True  # False -> do not show predictor config

    # others
    lang: 'zh'


################################### CLS #########################################
################### speech task: cls; engine_type: python #######################
cls_python:
    # model choices=['panns_cnn14', 'panns_cnn10', 'panns_cnn6']
    model: 'panns_cnn14'
    cfg_path: # [optional] Config of cls task.
    ckpt_path: # [optional] Checkpoint file of model.
    label_file: # [optional] Label file of cls task.
    device:  # set 'gpu:id' or 'cpu'


################### speech task: cls; engine_type: inference #######################
cls_inference:
    # model_type choices=['panns_cnn14', 'panns_cnn10', 'panns_cnn6']
    model_type: 'panns_cnn14' 
    cfg_path: 
    model_path:  # the pdmodel file of am static model [optional]
    params_path:  # the pdiparams file of am static model [optional]
    label_file:  # [optional] Label file of cls task.

    predictor_conf:
        device:  # set 'gpu:id' or 'cpu'
        switch_ir_optim: True
        glog_info: False  # True -> print glog
        summary: True  # False -> do not show predictor config


################################### Text #########################################
################### text task: punc; engine_type: python #######################
text_python:
    task: punc
    model_type: 'ernie_linear_p3_wudao'
    lang: 'zh'
    sample_rate: 16000
    cfg_path: # [optional]
    ckpt_path: # [optional]
    vocab_file: # [optional]
    device:  # set 'gpu:id' or 'cpu'


################################### Vector ######################################
################### Vector task: spk; engine_type: python #######################
vector_python:
    task: spk
    model_type: 'ecapatdnn_voxceleb12'
    sample_rate: 16000
    cfg_path: # [optional]
    ckpt_path: # [optional]
    device:  # set 'gpu:id' or 'cpu'