From 82530ddf974a706df5a6a1e258d80c8dbc3f1d72 Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期一, 10 六月 2024 09:19:16 +0800
Subject: [PATCH] fix bug
---
examples/industrial_data_pretraining/llm_asr/demo_speech2text.sh | 41 +++++++++++++++++++++--------------------
1 files changed, 21 insertions(+), 20 deletions(-)
diff --git a/examples/industrial_data_pretraining/llm_asr/demo_speech2text.sh b/examples/industrial_data_pretraining/llm_asr/demo_speech2text.sh
index 4f521f2..d7bd1cb 100644
--- a/examples/industrial_data_pretraining/llm_asr/demo_speech2text.sh
+++ b/examples/industrial_data_pretraining/llm_asr/demo_speech2text.sh
@@ -1,20 +1,21 @@
-
-
-ckpt_dir="/nfs/zhifu.gzf/ckpt/saves/qwen_1.5_7b/full/sft/asr_tts_text_exp1_ds_z3/checkpoint-11000"
+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="${ckpt_dir}/asr"
+out_dir="${ckpt_dir}/inference-${ckpt_id}"
mkdir -p ${out_dir}
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}/${data_set}
-
- pred_file=${out_dir}/${data_set}/1best_recog/text_tn
- ref_file=${out_dir}/${data_set}/1best_recog/label
+ 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} ${device}
@@ -26,11 +27,11 @@
for data_set in "aishell1_test_speech2text.jsonl" "aishell2_ios_test_speech2text.jsonl" "librispeech_test_other_speech2text.jsonl"; do
jsonl=${jsonl_dir}/${data_set}
output_dir=${out_dir}/${data_set}
+ mkdir -p ${output_dir}
+ pred_file=${output_dir}/1best_recog/text_tn
+ ref_file=${output_dir}/1best_recog/label
- pred_file=${out_dir}/${data_set}/1best_recog/text_tn
- ref_file=${out_dir}/${data_set}/1best_recog/label
-
- python ./demo_speech2text.py ${ckpt_dir} ${ckpt_id} ${jsonl} ${output_dir}
+ 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
@@ -39,11 +40,11 @@
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=${output_dir}/1best_recog/label
- pred_file=${out_dir}/${data_set}/1best_recog/text_tn
- ref_file=${out_dir}/${data_set}/1best_recog/label
-
- python ./demo_speech2text.py ${ckpt_dir} ${ckpt_id} ${jsonl} ${output_dir}
+ 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
@@ -52,12 +53,12 @@
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=${output_dir}/1best_recog/label
- pred_file=${out_dir}/${data_set}/1best_recog/text_tn
- ref_file=${out_dir}/${data_set}/1best_recog/label
+ python ./demo_speech2text.py ${ckpt_dir} ${ckpt_id} ${jsonl} ${output_dir} ${device}
- python ./demo_speech2text.py ${ckpt_dir} ${ckpt_id} ${jsonl} ${output_dir}
-
- python /mnt/workspace/zhifu.gzf/codebase/FunASR/funasr/metrics/wer.py ++ref_file=${ref_file} ++hyp_file=${pred_file} ++cer_file=${pred_file}.cer ++cn_postprocess=true
+ 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
--
Gitblit v1.9.1