aishell example

游雁

2024-02-19 6f3005e0632a616e4a7c492d9acf5062bef3bbb0

 examples/aishell/paraformer/run.sh

@@ -1,13 +1,8 @@
#!/usr/bin/env bash

workspace=`pwd`

# machines configuration

CUDA_VISIBLE_DEVICES="0,1"
gpu_num=2
gpu_inference=true  # Whether to perform gpu decoding, set false for cpu decoding
# for gpu decoding, inference_nj=ngpu*njob; for cpu decoding, inference_nj=njob
njob=1

# general configuration
feats_dir="../DATA" #feature output dictionary
@@ -18,7 +13,11 @@
stop_stage=5

# feature configuration
nj=64
nj=32

inference_device="cuda" #"cpu"
inference_checkpoint="model.pt"
inference_scp="wav.scp"

# data
raw_data=../raw_data
@@ -26,6 +25,7 @@

# exp tag
tag="exp1"
workspace=`pwd`

. utils/parse_options.sh || exit 1;

@@ -41,11 +41,6 @@

config=train_asr_paraformer_conformer_12e_6d_2048_256.yaml
model_dir="baseline_$(basename "${config}" .yaml)_${lang}_${token_type}_${tag}"

inference_device="cuda" #"cpu"
inference_checkpoint="model.pt"
inference_scp="wav.scp"



if [ ${stage} -le -1 ] && [ ${stop_stage} -ge -1 ]; then
@@ -112,6 +107,8 @@
  mkdir -p ${exp_dir}/exp/${model_dir}
  log_file="${exp_dir}/exp/${model_dir}/train.log.txt"
  echo "log_file: ${log_file}"

  gpu_num=$(echo CUDA_VISIBLE_DEVICES | awk -F "," '{print NF}')
  torchrun \
  --nnodes 1 \
  --nproc_per_node ${gpu_num} \
@@ -119,6 +116,7 @@
  --config-path "${workspace}/conf" \
  --config-name "${config}" \
  ++train_data_set_list="${feats_dir}/data/${train_set}/audio_datasets.jsonl" \
  ++valid_data_set_list="${feats_dir}/data/${valid_set}/audio_datasets.jsonl" \
  ++tokenizer_conf.token_list="${token_list}" \
  ++frontend_conf.cmvn_file="${feats_dir}/data/${train_set}/am.mvn" \
  ++output_dir="${exp_dir}/exp/${model_dir}" &> ${log_file}