Merge pull request #420 from alibaba-damo-academy/dev_lhn

update infer recipe

egs_modelscope/asr/TEMPLATE/infer.py

@@ -11,7 +11,7 @@ def modelscope_infer(args):
         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 @@ if __name__ == "__main__":
     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()

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)

egs_modelscope/asr/paraformer/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404/infer.py

@@ -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)

egs_modelscope/asr/paraformer/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404/infer.py

@@ -0,0 +1 @@
+../../TEMPLATE/infer.py

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
+

egs_modelscope/asr/paraformer/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404/utils

@@ -0,0 +1 @@
+../../../../egs/aishell/transformer/utils

egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-minnan-16k-common-vocab3825/infer.sh

@@ -9,12 +9,13 @@ stop_stage=2
 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 @@ if [ $stage -le 1 ] && [ $stop_stage -ge 1 ];then
             --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

egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-minnan-16k-common-vocab3825/utils

@@ -0,0 +1 @@
+../../../../egs/aishell/transformer/utils