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 | 93 +++++++++++++++++++++++-----------------------
1 files changed, 47 insertions(+), 46 deletions(-)
diff --git a/examples/industrial_data_pretraining/llm_asr/demo_speech2text.sh b/examples/industrial_data_pretraining/llm_asr/demo_speech2text.sh
index 64cc45b..57299fc 100644
--- a/examples/industrial_data_pretraining/llm_asr/demo_speech2text.sh
+++ b/examples/industrial_data_pretraining/llm_asr/demo_speech2text.sh
@@ -1,56 +1,18 @@
-ckpt_dir="/nfs/beinian.lzr/workspace/GPT-4o/Exp/exp6/5m-8gpu/exp6_speech2text_linear_ddp_0609"
-ckpt_id="model.pt.ep0.90000"
-jsonl_dir="/nfs/beinian.lzr/workspace/GPT-4o/Data/Speech2Text/TestData"
-out_dir="${ckpt_dir}/inference-${ckpt_id}"
-mkdir -p ${out_dir}
+ckpt_id="model.pt.ep0.90000"
device="cuda:0"
ckpt_id=$1
device=$2
-#for data_set in "librispeech_test_clean_speech2text.jsonl" "librispeech_test_other_speech2text.jsonl"; do
-# jsonl=${jsonl_dir}/${data_set}
-# output_dir=${out_dir}/${data_set}
-# mkdir -p ${output_dir}
-# pred_file=${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
+ckpt_dir="/nfs/beinian.lzr/workspace/GPT-4o/Exp/exp6/5m-8gpu/exp6_speech2text_linear_ddp_0609"
+jsonl_dir="/nfs/beinian.lzr/workspace/GPT-4o/Data/Speech2Text/TestData"
-
-for data_set in "aishell1_test_speech2text.jsonl" "aishell2_ios_test_speech2text.jsonl" "librispeech_test_other_speech2text.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=true
-
-done
-
-for data_set in "s2tt_en2zh.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=true
-
-done
-
-for data_set in "s2tt_zh2en.v20240605.test.jsonl"; do
+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 ${output_dir}
@@ -61,4 +23,43 @@
python /mnt/workspace/zhifu.gzf/codebase/FunASR/funasr/metrics/wer.py ++ref_file=${ref_file} ++hyp_file=${pred_file} ++cer_file=${pred_file}.cer ++cn_postprocess=false
-done
\ No newline at end of file
+}&
+done
+wait
+
+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 ${output_dir}
+ pred_file=${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=true
+
+}&
+done
+wait
+
+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 ${output_dir}
+ pred_file=${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}
+
+ 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
+wait
\ No newline at end of file
--
Gitblit v1.9.1