From 828948c2bca620f9d417745f07c88bbde94f58cc Mon Sep 17 00:00:00 2001
From: haoneng.lhn <haoneng.lhn@alibaba-inc.com>
Date: 星期二, 25 四月 2023 18:58:00 +0800
Subject: [PATCH] update infer recipe
---
egs_modelscope/asr/paraformer/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404/utils | 1
/dev/null | 21 -------
egs_modelscope/asr/TEMPLATE/infer.py | 3
egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-minnan-16k-common-vocab3825/infer.sh | 6 +
egs_modelscope/asr/paraformer/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404/infer.py | 1
egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-minnan-16k-common-vocab3825/utils | 1
egs_modelscope/asr/paraformer/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404/demo.py | 12 ++++
egs_modelscope/asr/paraformer/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404/infer.sh | 105 +++++++++++++++++++++++++++++++++++
8 files changed, 126 insertions(+), 24 deletions(-)
diff --git a/egs_modelscope/asr/TEMPLATE/infer.py b/egs_modelscope/asr/TEMPLATE/infer.py
index 629f93a..5bc205c 100644
--- a/egs_modelscope/asr/TEMPLATE/infer.py
+++ b/egs_modelscope/asr/TEMPLATE/infer.py
@@ -11,7 +11,7 @@
model=args.model,
output_dir=args.output_dir,
batch_size=args.batch_size,
- param_dict={"decoding_model": args.decoding_mode}
+ param_dict={"decoding_model": args.decoding_mode, "hotword": args.hotword_txt}
)
inference_pipeline(audio_in=args.audio_in)
@@ -21,6 +21,7 @@
parser.add_argument('--audio_in', type=str, default="./data/test/wav.scp")
parser.add_argument('--output_dir', type=str, default="./results/")
parser.add_argument('--decoding_mode', type=str, default="normal")
+ parser.add_argument('--hotword_txt', type=str, default=None)
parser.add_argument('--batch_size', type=int, default=64)
parser.add_argument('--gpuid', type=str, default="0")
args = parser.parse_args()
diff --git a/egs_modelscope/asr/paraformer/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404/demo.py b/egs_modelscope/asr/paraformer/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404/demo.py
new file mode 100644
index 0000000..bec6f05
--- /dev/null
+++ b/egs_modelscope/asr/paraformer/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404/demo.py
@@ -0,0 +1,12 @@
+from modelscope.pipelines import pipeline
+from modelscope.utils.constant import Tasks
+
+param_dict = dict()
+param_dict['hotword'] = "https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/hotword.txt"
+inference_pipeline = pipeline(
+ task=Tasks.auto_speech_recognition,
+ model="damo/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404",
+ param_dict=param_dict)
+
+rec_result = inference_pipeline(audio_in='https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_hotword.wav')
+print(rec_result)
diff --git a/egs_modelscope/asr/paraformer/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404/infer.py b/egs_modelscope/asr/paraformer/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404/infer.py
deleted file mode 100644
index 16a57e9..0000000
--- a/egs_modelscope/asr/paraformer/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404/infer.py
+++ /dev/null
@@ -1,21 +0,0 @@
-from modelscope.pipelines import pipeline
-from modelscope.utils.constant import Tasks
-
-
-if __name__ == '__main__':
- param_dict = dict()
- param_dict['hotword'] = "https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/hotword.txt"
-
- audio_in = "https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_hotword.wav"
- output_dir = None
- batch_size = 1
-
- inference_pipeline = pipeline(
- task=Tasks.auto_speech_recognition,
- model="damo/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404",
- output_dir=output_dir,
- batch_size=batch_size,
- param_dict=param_dict)
-
- rec_result = inference_pipeline(audio_in=audio_in)
- print(rec_result)
diff --git a/egs_modelscope/asr/paraformer/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404/infer.py b/egs_modelscope/asr/paraformer/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404/infer.py
new file mode 120000
index 0000000..128fc31
--- /dev/null
+++ b/egs_modelscope/asr/paraformer/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404/infer.py
@@ -0,0 +1 @@
+../../TEMPLATE/infer.py
\ No newline at end of file
diff --git a/egs_modelscope/asr/paraformer/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404/infer.sh b/egs_modelscope/asr/paraformer/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404/infer.sh
new file mode 100644
index 0000000..e60f6d9
--- /dev/null
+++ b/egs_modelscope/asr/paraformer/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404/infer.sh
@@ -0,0 +1,105 @@
+#!/usr/bin/env bash
+
+set -e
+set -u
+set -o pipefail
+
+stage=1
+stop_stage=2
+model="damo/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404"
+data_dir="./data/test"
+output_dir="./results"
+batch_size=64
+gpu_inference=true # whether to perform gpu decoding
+gpuid_list="0,1" # set gpus, e.g., gpuid_list="0,1"
+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"
+hotword_txt=None
+
+. utils/parse_options.sh || exit 1;
+
+if ${gpu_inference} == "true"; then
+ nj=$(echo $gpuid_list | awk -F "," '{print NF}')
+else
+ nj=$njob
+ batch_size=1
+ gpuid_list=""
+ for JOB in $(seq ${nj}); do
+ gpuid_list=$gpuid_list"-1,"
+ done
+fi
+
+mkdir -p $output_dir/split
+split_scps=""
+for JOB in $(seq ${nj}); do
+ split_scps="$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 ] && [ $stop_stage -ge 1 ];then
+ echo "Decoding ..."
+ gpuid_list_array=(${gpuid_list//,/ })
+ for JOB in $(seq ${nj}); do
+ {
+ id=$((JOB-1))
+ gpuid=${gpuid_list_array[$id]}
+ mkdir -p ${output_dir}/output.$JOB
+ python infer.py \
+ --model ${model} \
+ --audio_in ${output_dir}/split/wav.$JOB.scp \
+ --output_dir ${output_dir}/output.$JOB \
+ --batch_size ${batch_size} \
+ --gpuid ${gpuid} \
+ --hotword_txt ${hotword_txt}
+ }&
+ done
+ wait
+
+ mkdir -p ${output_dir}/1best_recog
+ for f in token score text; do
+ if [ -f "${output_dir}/output.1/1best_recog/${f}" ]; then
+ for i in $(seq "${nj}"); do
+ cat "${output_dir}/output.${i}/1best_recog/${f}"
+ done | sort -k1 >"${output_dir}/1best_recog/${f}"
+ fi
+ done
+fi
+
+if [ $stage -le 2 ] && [ $stop_stage -ge 2 ];then
+ echo "Computing WER ..."
+ 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
+
+if [ $stage -le 3 ] && [ $stop_stage -ge 3 ];then
+ echo "SpeechIO TIOBE textnorm"
+ echo "$0 --> Normalizing REF text ..."
+ ./utils/textnorm_zh.py \
+ --has_key --to_upper \
+ ${data_dir}/text \
+ ${output_dir}/1best_recog/ref.txt
+
+ echo "$0 --> Normalizing HYP text ..."
+ ./utils/textnorm_zh.py \
+ --has_key --to_upper \
+ ${output_dir}/1best_recog/text.proc \
+ ${output_dir}/1best_recog/rec.txt
+ grep -v $'\t$' ${output_dir}/1best_recog/rec.txt > ${output_dir}/1best_recog/rec_non_empty.txt
+
+ echo "$0 --> computing WER/CER and alignment ..."
+ ./utils/error_rate_zh \
+ --tokenizer char \
+ --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
+fi
+
diff --git a/egs_modelscope/asr/paraformer/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404/utils b/egs_modelscope/asr/paraformer/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404/utils
new file mode 120000
index 0000000..2ac163f
--- /dev/null
+++ b/egs_modelscope/asr/paraformer/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404/utils
@@ -0,0 +1 @@
+../../../../egs/aishell/transformer/utils
\ No newline at end of file
diff --git a/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-minnan-16k-common-vocab3825/infer.sh b/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-minnan-16k-common-vocab3825/infer.sh
index 448717d..b44be9f 100644
--- a/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-minnan-16k-common-vocab3825/infer.sh
+++ b/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-minnan-16k-common-vocab3825/infer.sh
@@ -9,12 +9,13 @@
model="damo/speech_UniASR_asr_2pass-minnan-16k-common-vocab3825"
data_dir="./data/test"
output_dir="./results"
-batch_size=64
+batch_size=1
gpu_inference=true # whether to perform gpu decoding
gpuid_list="0,1" # set gpus, e.g., gpuid_list="0,1"
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"
+decoding_mode="normal"
. utils/parse_options.sh || exit 1;
@@ -54,7 +55,8 @@
--audio_in ${output_dir}/split/wav.$JOB.scp \
--output_dir ${output_dir}/output.$JOB \
--batch_size ${batch_size} \
- --gpuid ${gpuid}
+ --gpuid ${gpuid} \
+ --decoding_mode ${decoding_mode}
}&
done
wait
diff --git a/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-minnan-16k-common-vocab3825/utils b/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-minnan-16k-common-vocab3825/utils
new file mode 120000
index 0000000..2ac163f
--- /dev/null
+++ b/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-minnan-16k-common-vocab3825/utils
@@ -0,0 +1 @@
+../../../../egs/aishell/transformer/utils
\ No newline at end of file
--
Gitblit v1.9.1