update infer recipe

egs_modelscope/asr/TEMPLATE/infer.py

@@ -11,6 +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}
     )
     inference_pipeline(audio_in=args.audio_in)
 
@@ -19,7 +20,8 @@ if __name__ == "__main__":
     parser.add_argument('--model', type=str, default="damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch")
     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('--batch_size', type=int, default=64)
     parser.add_argument('--gpuid', type=str, default="0")
     args = parser.parse_args()
-    modelscope_infer(args)
+    modelscope_infer(args)

egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/demo.py

@@ -0,0 +1,9 @@
+from modelscope.pipelines import pipeline
+from modelscope.utils.constant import Tasks
+
+inference_pipeline = pipeline(
+    task=Tasks.auto_speech_recognition,
+    model='damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch')
+
+rec_result = inference_pipeline(audio_in='https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav')
+print(rec_result)

egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/infer.py

@@ -1,25 +0,0 @@
-import os
-import shutil
-import argparse
-from modelscope.pipelines import pipeline
-from modelscope.utils.constant import Tasks
-
-def modelscope_infer(args):
-    os.environ['CUDA_VISIBLE_DEVICES'] = str(args.gpuid)
-    inference_pipeline = pipeline(
-        task=Tasks.auto_speech_recognition,
-        model=args.model,
-        output_dir=args.output_dir,
-        batch_size=args.batch_size,
-    )
-    inference_pipeline(audio_in=args.audio_in)
-
-if __name__ == "__main__":
-    parser = argparse.ArgumentParser()
-    parser.add_argument('--model', type=str, default="damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch")
-    parser.add_argument('--audio_in', type=str, default="./data/test/wav.scp")
-    parser.add_argument('--output_dir', type=str, default="./results/")
-    parser.add_argument('--batch_size', type=int, default=64)
-    parser.add_argument('--gpuid', type=str, default="0")
-    args = parser.parse_args()
-    modelscope_infer(args)

egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/infer.py

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

egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/infer.sh

@@ -12,7 +12,9 @@ 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=4    # the number of jobs for CPU decoding, if gpu_inference=false, use CPU decoding, please set njob
+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"
 
 . utils/parse_options.sh || exit 1;
 
@@ -34,6 +36,11 @@ for JOB in $(seq ${nj}); do
 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//,/ })

egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-minnan-16k-common-vocab3825/demo.py

@@ -0,0 +1,12 @@
+from modelscope.pipelines import pipeline
+from modelscope.utils.constant import Tasks
+
+decoding_mode="normal" #fast, normal, offline
+inference_pipeline = pipeline(
+    task=Tasks.auto_speech_recognition,
+    model='damo/speech_UniASR_asr_2pass-minnan-16k-common-vocab3825',
+    param_dict={"decoding_model": decoding_mode}
+)
+
+rec_result = inference_pipeline(audio_in='https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav')
+print(rec_result)

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

@@ -1,89 +0,0 @@
-import os
-import shutil
-from multiprocessing import Pool
-
-from modelscope.pipelines import pipeline
-from modelscope.utils.constant import Tasks
-
-from funasr.utils.compute_wer import compute_wer
-
-
-def modelscope_infer_core(output_dir, split_dir, njob, idx):
-    output_dir_job = os.path.join(output_dir, "output.{}".format(idx))
-    gpu_id = (int(idx) - 1) // njob
-    if "CUDA_VISIBLE_DEVICES" in os.environ.keys():
-        gpu_list = os.environ['CUDA_VISIBLE_DEVICES'].split(",")
-        os.environ['CUDA_VISIBLE_DEVICES'] = str(gpu_list[gpu_id])
-    else:
-        os.environ['CUDA_VISIBLE_DEVICES'] = str(gpu_id)
-    inference_pipline = pipeline(
-        task=Tasks.auto_speech_recognition,
-        model="damo/speech_UniASR_asr_2pass-minnan-16k-common-vocab3825",
-        output_dir=output_dir_job,
-        batch_size=1
-    )
-    audio_in = os.path.join(split_dir, "wav.{}.scp".format(idx))
-    inference_pipline(audio_in=audio_in, param_dict={"decoding_model": "normal"})
-
-
-def modelscope_infer(params):
-    # prepare for multi-GPU decoding
-    ngpu = params["ngpu"]
-    njob = params["njob"]
-    output_dir = params["output_dir"]
-    if os.path.exists(output_dir):
-        shutil.rmtree(output_dir)
-    os.mkdir(output_dir)
-    split_dir = os.path.join(output_dir, "split")
-    os.mkdir(split_dir)
-    nj = ngpu * njob
-    wav_scp_file = os.path.join(params["data_dir"], "wav.scp")
-    with open(wav_scp_file) as f:
-        lines = f.readlines()
-        num_lines = len(lines)
-        num_job_lines = num_lines // nj
-    start = 0
-    for i in range(nj):
-        end = start + num_job_lines
-        file = os.path.join(split_dir, "wav.{}.scp".format(str(i + 1)))
-        with open(file, "w") as f:
-            if i == nj - 1:
-                f.writelines(lines[start:])
-            else:
-                f.writelines(lines[start:end])
-        start = end
-
-    p = Pool(nj)
-    for i in range(nj):
-        p.apply_async(modelscope_infer_core,
-                      args=(output_dir, split_dir, njob, str(i + 1)))
-    p.close()
-    p.join()
-
-    # combine decoding results
-    best_recog_path = os.path.join(output_dir, "1best_recog")
-    os.mkdir(best_recog_path)
-    files = ["text", "token", "score"]
-    for file in files:
-        with open(os.path.join(best_recog_path, file), "w") as f:
-            for i in range(nj):
-                job_file = os.path.join(output_dir, "output.{}/1best_recog".format(str(i + 1)), file)
-                with open(job_file) as f_job:
-                    lines = f_job.readlines()
-                f.writelines(lines)
-
-    # If text exists, compute CER
-    text_in = os.path.join(params["data_dir"], "text")
-    if os.path.exists(text_in):
-        text_proc_file = os.path.join(best_recog_path, "token")
-        compute_wer(text_in, text_proc_file, os.path.join(best_recog_path, "text.cer"))
-        os.system("tail -n 3 {}".format(os.path.join(best_recog_path, "text.cer")))
-
-
-if __name__ == "__main__":
-    params = {}
-    params["data_dir"] = "./data/test"
-    params["output_dir"] = "./results"
-    params["ngpu"] = 1
-    params["njob"] = 8
-    modelscope_infer(params)

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

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

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

@@ -0,0 +1,103 @@
+#!/usr/bin/env bash
+
+set -e
+set -u
+set -o pipefail
+
+stage=1
+stop_stage=2
+model="damo/speech_UniASR_asr_2pass-minnan-16k-common-vocab3825"
+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"
+
+. 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}
+        }&
+    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
+