PaddleSpeech/examples/tiny/asr0/conf/deepspeech2.yaml

# https://yaml.org/type/float.html
###########################################
#                   Data                  #
###########################################
train_manifest: data/manifest.tiny
dev_manifest: data/manifest.tiny
test_manifest: data/manifest.tiny 
min_input_len: 0.0
max_input_len: 30.0
min_output_len: 0.0
max_output_len: 400.0
min_output_input_ratio: 0.05
max_output_input_ratio: 10.0


###########################################
#              Dataloader                 #
###########################################
vocab_filepath: data/lang_char/vocab.txt 
spm_model_prefix: ''
unit_type: 'char'
preprocess_config: conf/preprocess.yaml
feat_dim: 161
stride_ms: 10.0
window_ms: 25.0
sortagrad: 0 # Feed samples from shortest to longest ; -1: enabled for all epochs, 0: disabled, other: enabled for 'other' epochs 
batch_size: 4
maxlen_in: 512  # if input length  > maxlen-in, batchsize is automatically reduced
maxlen_out: 150  # if output length > maxlen-out, batchsize is automatically reduced
minibatches: 0 # for debug
batch_count: auto
batch_bins: 0 
batch_frames_in: 0
batch_frames_out: 0
batch_frames_inout: 0
num_workers: 8
subsampling_factor: 1
num_encs: 1
  
############################################
#           Network Architecture           #
############################################
num_conv_layers: 2
num_rnn_layers: 3
rnn_layer_size: 2048
rnn_direction: bidirect # [forward, bidirect]
num_fc_layers: 0
fc_layers_size_list: -1,
use_gru: False 
blank_id: 0
  

###########################################
#                Training                 #
###########################################
n_epoch: 5
accum_grad: 1
lr: 1.0e-5 
lr_decay: 0.8 
weight_decay: 1.0e-6
global_grad_clip: 5.0
dist_sampler: False
log_interval: 1
checkpoint:
  kbest_n: 3
  latest_n: 2