From c2dee5e3c29eba79e591d9e9caebaef15ea4e56b Mon Sep 17 00:00:00 2001
From: hnluo <haoneng.lhn@alibaba-inc.com>
Date: 星期四, 29 六月 2023 11:09:28 +0800
Subject: [PATCH] Merge pull request #687 from alibaba-damo-academy/dev_lhn
---
egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/infer.sh | 22 +++++++++++++++-------
1 files changed, 15 insertions(+), 7 deletions(-)
diff --git a/egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/infer.sh b/egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/infer.sh
index ab64849..ef49d7a 100644
--- a/egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/infer.sh
+++ b/egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/infer.sh
@@ -12,10 +12,13 @@
batch_size=64
gpu_inference=true # whether to perform gpu decoding
gpuid_list="0,1" # set gpus, e.g., gpuid_list="0,1"
-njob=4 # the number of jobs for CPU decoding, if gpu_inference=false, use CPU decoding, please set njob
+njob=64 # the number of jobs for CPU decoding, if gpu_inference=false, use CPU decoding, please set njob
+checkpoint_dir=
+checkpoint_name="valid.cer_ctc.ave.pb"
+. utils/parse_options.sh || exit 1;
-if ${gpu_inference}; then
+if ${gpu_inference} == "true"; then
nj=$(echo $gpuid_list | awk -F "," '{print NF}')
else
nj=$njob
@@ -32,6 +35,11 @@
split_scps="$split_scps $output_dir/split/wav.$JOB.scp"
done
perl utils/split_scp.pl ${data_dir}/wav.scp ${split_scps}
+
+if [ -n "${checkpoint_dir}" ]; then
+ python utils/prepare_checkpoint.py ${model} ${checkpoint_dir} ${checkpoint_name}
+ model=${checkpoint_dir}/${model}
+fi
if [ $stage -le 1 ] && [ $stop_stage -ge 1 ];then
echo "Decoding ..."
@@ -63,9 +71,9 @@
if [ $stage -le 2 ] && [ $stop_stage -ge 2 ];then
echo "Computing WER ..."
- python utils/proce_text.py ${output_dir}/1best_recog/text ${output_dir}/1best_recog/text.proc
- python utils/proce_text.py ${data_dir}/text ${data_dir}/text.proc
- python utils/compute_wer.py ${data_dir}/text.proc ${output_dir}/1best_recog/text.proc ${output_dir}/1best_recog/text.cer
+ cp ${output_dir}/1best_recog/text ${output_dir}/1best_recog/text.proc
+ cp ${data_dir}/text ${output_dir}/1best_recog/text.ref
+ python utils/compute_wer.py ${output_dir}/1best_recog/text.ref ${output_dir}/1best_recog/text.proc ${output_dir}/1best_recog/text.cer
tail -n 3 ${output_dir}/1best_recog/text.cer
fi
@@ -75,7 +83,7 @@
./utils/textnorm_zh.py \
--has_key --to_upper \
${data_dir}/text \
- ${data_dir}/ref.txt
+ ${output_dir}/1best_recog/ref.txt
echo "$0 --> Normalizing HYP text ..."
./utils/textnorm_zh.py \
@@ -87,7 +95,7 @@
echo "$0 --> computing WER/CER and alignment ..."
./utils/error_rate_zh \
--tokenizer char \
- --ref ${data_dir}/ref.txt \
+ --ref ${output_dir}/1best_recog/ref.txt \
--hyp ${output_dir}/1best_recog/rec_non_empty.txt \
${output_dir}/1best_recog/DETAILS.txt | tee ${output_dir}/1best_recog/RESULTS.txt
rm -rf ${output_dir}/1best_recog/rec.txt ${output_dir}/1best_recog/rec_non_empty.txt
--
Gitblit v1.9.1