From 3d9f094e9652d4b84894c6fd4eae39a4a753b0f0 Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期二, 16 五月 2023 23:48:00 +0800
Subject: [PATCH] train
---
egs/aishell/data2vec_transformer_finetune/run.sh | 24 +++++++++++++++---------
1 files changed, 15 insertions(+), 9 deletions(-)
diff --git a/egs/aishell/data2vec_transformer_finetune/run.sh b/egs/aishell/data2vec_transformer_finetune/run.sh
index 1583b9e..7a28e3b 100755
--- a/egs/aishell/data2vec_transformer_finetune/run.sh
+++ b/egs/aishell/data2vec_transformer_finetune/run.sh
@@ -20,8 +20,8 @@
type=sound
scp=wav.scp
speed_perturb="0.9 1.0 1.1"
-stage=3
-stop_stage=4
+stage=0
+stop_stage=5
# feature configuration
feats_dim=80
@@ -53,7 +53,7 @@
model_dir="baseline_$(basename "${asr_config}" .yaml)_${lang}_${token_type}_${tag}"
inference_config=conf/decode_asr_transformer.yaml
-inference_asr_model=valid.acc.ave_10best.pb
+inference_asr_model=valid.cer_ctc.ave_10best.pb
# you can set gpu num for decoding here
gpuid_list=$CUDA_VISIBLE_DEVICES # set gpus for decoding, the same as training stage by default
@@ -106,11 +106,17 @@
echo "<unk>" >> ${token_list}
fi
-# Training Stage
+# LM Training Stage
world_size=$gpu_num # run on one machine
if [ ${stage} -le 3 ] && [ ${stop_stage} -ge 3 ]; then
- echo "stage 3: Training"
- python utils/download_model.py --model_name ${model_name} # download pretrained model on ModelScope
+ echo "stage 3: LM Training"
+fi
+
+# ASR Training Stage
+world_size=$gpu_num # run on one machine
+if [ ${stage} -le 4 ] && [ ${stop_stage} -ge 4 ]; then
+ echo "stage 4: ASR Training"
+ python utils/download_model.py --model_name ${model_name} # download pretrained model on ModelScope
mkdir -p ${exp_dir}/exp/${model_dir}
mkdir -p ${exp_dir}/exp/${model_dir}/log
INIT_FILE=${exp_dir}/exp/${model_dir}/ddp_init
@@ -151,8 +157,8 @@
fi
# Testing Stage
-if [ ${stage} -le 4 ] && [ ${stop_stage} -ge 4 ]; then
- echo "stage 4: Inference"
+if [ ${stage} -le 5 ] && [ ${stop_stage} -ge 5 ]; then
+ echo "stage 5: Inference"
for dset in ${test_sets}; do
asr_exp=${exp_dir}/exp/${model_dir}
inference_tag="$(basename "${inference_config}" .yaml)"
@@ -189,7 +195,7 @@
--asr_train_config "${asr_exp}"/config.yaml \
--asr_model_file "${asr_exp}"/"${inference_asr_model}" \
--output_dir "${_logdir}"/output.JOB \
- --mode paraformer \
+ --mode asr \
${_opts}
for f in token token_int score text; do
--
Gitblit v1.9.1