You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
85 lines
3.3 KiB
85 lines
3.3 KiB
# This is the parameter configuration file for PaddleSpeech 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_online-inference', 'asr_online-onnx']
|
|
# protocol = ['websocket'] (only one can be selected).
|
|
# websocket only support online engine type.
|
|
protocol: 'websocket'
|
|
engine_list: ['asr_online-onnx']
|
|
|
|
|
|
#################################################################################
|
|
# ENGINE CONFIG #
|
|
#################################################################################
|
|
|
|
################################### ASR #########################################
|
|
################### speech task: asr; engine_type: online-inference #######################
|
|
asr_online-inference:
|
|
model_type: 'deepspeech2online_wenetspeech'
|
|
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:
|
|
num_decoding_left_chunks:
|
|
force_yes: True
|
|
device: 'cpu' # cpu or gpu:id
|
|
|
|
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
|
|
|
|
chunk_buffer_conf:
|
|
frame_duration_ms: 85
|
|
shift_ms: 40
|
|
sample_rate: 16000
|
|
sample_width: 2
|
|
window_n: 7 # frame
|
|
shift_n: 4 # frame
|
|
window_ms: 25 # ms
|
|
shift_ms: 10 # ms
|
|
|
|
|
|
|
|
################################### ASR #########################################
|
|
################### speech task: asr; engine_type: online-onnx #######################
|
|
asr_online-onnx:
|
|
model_type: 'deepspeech2online_wenetspeech'
|
|
am_model: # the pdmodel file of onnx am static model [optional]
|
|
am_params: # the pdiparams file of am static model [optional]
|
|
lang: 'zh'
|
|
sample_rate: 16000
|
|
cfg_path:
|
|
decode_method:
|
|
num_decoding_left_chunks:
|
|
force_yes: True
|
|
device: 'cpu' # cpu or gpu:id
|
|
|
|
# https://onnxruntime.ai/docs/api/python/api_summary.html#inferencesession
|
|
am_predictor_conf:
|
|
device: 'cpu' # set 'gpu:id' or 'cpu'
|
|
graph_optimization_level: 0
|
|
intra_op_num_threads: 0 # Sets the number of threads used to parallelize the execution within nodes.
|
|
inter_op_num_threads: 0 # Sets the number of threads used to parallelize the execution of the graph (across nodes).
|
|
log_severity_level: 2 # Log severity level. Applies to session load, initialization, etc. 0:Verbose, 1:Info, 2:Warning. 3:Error, 4:Fatal. Default is 2.
|
|
log_verbosity_level: 0 # VLOG level if DEBUG build and session_log_severity_level is 0. Applies to session load, initialization, etc. Default is 0.
|
|
|
|
chunk_buffer_conf:
|
|
frame_duration_ms: 80
|
|
shift_ms: 40
|
|
sample_rate: 16000
|
|
sample_width: 2
|
|
window_n: 7 # frame
|
|
shift_n: 4 # frame
|
|
window_ms: 25 # ms
|
|
shift_ms: 10 # ms
|