From 1596f6f414f6f41da66506debb1dff19fffeb3ec Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期一, 24 六月 2024 11:55:17 +0800
Subject: [PATCH] fixbug hotwords
---
examples/industrial_data_pretraining/llm_asr/demo_speech2text.sh | 34 +++++++++++++++++-----------------
1 files changed, 17 insertions(+), 17 deletions(-)
diff --git a/examples/industrial_data_pretraining/llm_asr/demo_speech2text.sh b/examples/industrial_data_pretraining/llm_asr/demo_speech2text.sh
index d4c409b..57299fc 100644
--- a/examples/industrial_data_pretraining/llm_asr/demo_speech2text.sh
+++ b/examples/industrial_data_pretraining/llm_asr/demo_speech2text.sh
@@ -12,6 +12,7 @@
out_dir="${ckpt_dir}/inference-${ckpt_id}"
mkdir -p ${out_dir}
for data_set in "librispeech_test_clean_speech2text.jsonl" "librispeech_test_other_speech2text.jsonl"; do
+{
jsonl=${jsonl_dir}/${data_set}
output_dir=${out_dir}/${data_set}
mkdir -p ${output_dir}
@@ -22,10 +23,12 @@
python /mnt/workspace/zhifu.gzf/codebase/FunASR/funasr/metrics/wer.py ++ref_file=${ref_file} ++hyp_file=${pred_file} ++cer_file=${pred_file}.cer ++cn_postprocess=false
+}&
done
+wait
-
-for data_set in "aishell1_test_speech2text.jsonl" "aishell2_ios_test_speech2text.jsonl" "librispeech_test_other_speech2text.jsonl"; do
+for data_set in "aishell1_test_speech2text.jsonl" "aishell2_ios_test_speech2text.jsonl"; do
+{
jsonl=${jsonl_dir}/${data_set}
output_dir=${out_dir}/${data_set}
mkdir -p ${output_dir}
@@ -36,9 +39,12 @@
python /mnt/workspace/zhifu.gzf/codebase/FunASR/funasr/metrics/wer.py ++ref_file=${ref_file} ++hyp_file=${pred_file} ++cer_file=${pred_file}.cer ++cn_postprocess=true
+}&
done
+wait
-for data_set in "s2tt_en2zh.v20240605.test.jsonl"; do
+for data_set in "common_voice_zh-CN_speech2text.jsonl" "common_voice_en_speech2text.jsonl"; do
+{
jsonl=${jsonl_dir}/${data_set}
output_dir=${out_dir}/${data_set}
mkdir -p ${output_dir}
@@ -47,19 +53,13 @@
python ./demo_speech2text.py ${ckpt_dir} ${ckpt_id} ${jsonl} ${output_dir} ${device}
- python /mnt/workspace/zhifu.gzf/codebase/FunASR/funasr/metrics/wer.py ++ref_file=${ref_file} ++hyp_file=${pred_file} ++cer_file=${pred_file}.cer ++cn_postprocess=true
+ cn_postprocess=false
+ if [ $data_set = "common_voice_zh-CN_speech2text.jsonl" ];then
+ cn_postprocess=true
+ fi
+ python /mnt/workspace/zhifu.gzf/codebase/FunASR/funasr/metrics/wer.py ++ref_file=${ref_file} ++hyp_file=${pred_file} ++cer_file=${pred_file}.cer ++cn_postprocess=${cn_postprocess}
+
+}&
done
-
-for data_set in "s2tt_zh2en.v20240605.test.jsonl"; do
- jsonl=${jsonl_dir}/${data_set}
- output_dir=${out_dir}/${data_set}
- mkdir -p ${output_dir}
- pred_file=${output_dir}/1best_recog/text_tn
- ref_file=${output_dir}/1best_recog/label
-
- python ./demo_speech2text.py ${ckpt_dir} ${ckpt_id} ${jsonl} ${output_dir} ${device}
-
- python /mnt/workspace/zhifu.gzf/codebase/FunASR/funasr/metrics/wer.py ++ref_file=${ref_file} ++hyp_file=${pred_file} ++cer_file=${pred_file}.cer ++cn_postprocess=false
-
-done
\ No newline at end of file
+wait
\ No newline at end of file
--
Gitblit v1.9.1