From 5ca83889c2774d86178427b859c8acba3f9a9ee5 Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期一, 10 六月 2024 10:10:47 +0800
Subject: [PATCH] fix bug
---
examples/industrial_data_pretraining/llm_asr/demo_speech2text.sh | 35 ++++++++++++++++++-----------------
1 files changed, 18 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 64cc45b..d4c409b 100644
--- a/examples/industrial_data_pretraining/llm_asr/demo_speech2text.sh
+++ b/examples/industrial_data_pretraining/llm_asr/demo_speech2text.sh
@@ -1,27 +1,28 @@
-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"
+
+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 ${output_dir}
+ pred_file=${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
for data_set in "aishell1_test_speech2text.jsonl" "aishell2_ios_test_speech2text.jsonl" "librispeech_test_other_speech2text.jsonl"; do
--
Gitblit v1.9.1