update paraformer recipe

2025-09-15 14:48:36 +08:00 · 2023-03-22 19:27:15 +08:00 · 2023-03-22 19:27:15 +08:00 · a0879e4663
commit a0879e4663
parent d3e785f6ab
6 changed files with 125 additions and 102 deletions
--- a/egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/infer.py
+++ b/egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/infer.py
@ -16,7 +16,7 @@ def modelscope_infer(args):

 if __name__ == "__main__":
    parser = argparse.ArgumentParser()
-    parser.add_argument('--model', type=str, default="speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch")
+    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")
    parser.add_argument('--output_dir', type=str, default="./results/")
    parser.add_argument('--batch_size', type=int, default=64)
--- a/egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/infer.sh
+++ b/egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/infer.sh
@ -64,8 +64,8 @@ fi
 if [ $stage -le 2 ] && [ $stop_stage -ge 2 ];then
    echo "Computing WER ..."
    python utils/proce_text.py ${output_dir}/1best_recog/text ${output_dir}/1best_recog/text.proc
-    python utils/proce_text.py ${data_dir}/text ${data_dir}/text.proc
-    python utils/compute_wer.py ${data_dir}/text.proc ${output_dir}/1best_recog/text.proc ${output_dir}/1best_recog/text.cer
+    python utils/proce_text.py ${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

@ -75,7 +75,7 @@ if [ $stage -le 3 ] && [ $stop_stage -ge 3 ];then
    ./utils/textnorm_zh.py \
        --has_key --to_upper \
        ${data_dir}/text \
-        ${data_dir}/ref.txt
+        ${output_dir}/1best_recog/ref.txt

    echo "$0 --> Normalizing HYP text ..."
    ./utils/textnorm_zh.py \
@ -87,7 +87,7 @@ if [ $stage -le 3 ] && [ $stop_stage -ge 3 ];then
    echo "$0 --> computing WER/CER and alignment ..."
    ./utils/error_rate_zh \
        --tokenizer char \
-        --ref ${data_dir}/ref.txt \
+        --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
--- a/egs_modelscope/asr/paraformer/speech_paraformer_asr_nat-zh-cn-8k-common-vocab8358-tensorflow1/README.md
+++ b/egs_modelscope/asr/paraformer/speech_paraformer_asr_nat-zh-cn-8k-common-vocab8358-tensorflow1/README.md
@ -6,8 +6,9 @@

 - Modify finetune training related parameters in `finetune.py`
    - <strong>output_dir:</strong> # result dir
-    - <strong>data_dir:</strong> # the dataset dir needs to include files: train/wav.scp, train/text; validation/wav.scp, validation/text.
-    - <strong>batch_bins:</strong> # batch size
+    - <strong>data_dir:</strong> # the dataset dir needs to include files: `train/wav.scp`, `train/text`; `validation/wav.scp`, `validation/text`
+    - <strong>dataset_type:</strong> # for dataset larger than 1000 hours, set as `large`, otherwise set as `small`
+    - <strong>batch_bins:</strong> # batch size. For dataset_type is `small`, `batch_bins` indicates the feature frames. For dataset_type is `large`, `batch_bins` indicates the duration in ms
    - <strong>max_epoch:</strong> # number of training epoch
    - <strong>lr:</strong> # learning rate

@ -20,11 +21,38 @@

 Or you can use the finetuned model for inference directly.

- Setting parameters in `infer.py`
-    - <strong>data_dir:</strong> # the dataset dir
+- Setting parameters in `infer.sh`
+    - <strong>model:</strong> # model name on ModelScope
+    - <strong>data_dir:</strong> # the dataset dir needs to include `test/wav.scp`. If `test/text` is also exists, CER will be computed
    - <strong>output_dir:</strong> # result dir
+    - <strong>batch_size:</strong> # batchsize of inference
+    - <strong>gpu_inference:</strong> # whether to perform gpu decoding, set false for cpu decoding
+    - <strong>gpuid_list:</strong> # set gpus, e.g., gpuid_list="0,1"
+    - <strong>njob:</strong> # the number of jobs for CPU decoding, if `gpu_inference`=false, use CPU decoding, please set `njob`

 - Then you can run the pipeline to infer with:
 ```python
-    python infer.py
+    sh infer.sh
 ```
+
+- Results
+
+The decoding results can be found in `$output_dir/1best_recog/text.cer`, which includes recognition results of each sample and the CER metric of the whole test set.
+
+### Inference using local finetuned model
+
+- Modify inference related parameters in `infer_after_finetune.py`
+    - <strong>modelscope_model_name: </strong> # model name on ModelScope
+    - <strong>output_dir:</strong> # result dir
+    - <strong>data_dir:</strong> # the dataset dir needs to include `test/wav.scp`. If `test/text` is also exists, CER will be computed
+    - <strong>decoding_model_name:</strong> # set the checkpoint name for decoding, e.g., `valid.cer_ctc.ave.pb`
+    - <strong>batch_size:</strong> # batchsize of inference  
+
+- Then you can run the pipeline to finetune with:
+```python
+    python infer_after_finetune.py
+```
+
+- Results
+
+The decoding results can be found in `$output_dir/decoding_results/text.cer`, which includes recognition results of each sample and the CER metric of the whole test set.
--- a/egs_modelscope/asr/paraformer/speech_paraformer_asr_nat-zh-cn-8k-common-vocab8358-tensorflow1/infer.py
+++ b/egs_modelscope/asr/paraformer/speech_paraformer_asr_nat-zh-cn-8k-common-vocab8358-tensorflow1/infer.py
@ -1,101 +1,25 @@
 import os
 import shutil
-from multiprocessing import Pool
-
+import argparse
 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, batch_size, ngpu, model):
-    output_dir_job = os.path.join(output_dir, "output.{}".format(idx))
-    if ngpu > 0:
-        use_gpu = 1
-        gpu_id = int(idx) - 1
-    else:
-        use_gpu = 0
-        gpu_id = -1
-    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(
+def modelscope_infer(args):
+    os.environ['CUDA_VISIBLE_DEVICES'] = str(args.gpuid)
+    inference_pipeline = pipeline(
        task=Tasks.auto_speech_recognition,
-        model=model,
-        output_dir=output_dir_job,
-        batch_size=batch_size,
-        ngpu=use_gpu,
+        model=args.model,
+        output_dir=args.output_dir,
+        batch_size=args.batch_size,
    )
-    audio_in = os.path.join(split_dir, "wav.{}.scp".format(idx))
-    inference_pipline(audio_in=audio_in)
-
-
-def modelscope_infer(params):
-    # prepare for multi-GPU decoding
-    ngpu = params["ngpu"]
-    njob = params["njob"]
-    batch_size = params["batch_size"]
-    output_dir = params["output_dir"]
-    model = params["model"]
-    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)
-    if ngpu > 0:
-        nj = ngpu
-    elif ngpu == 0:
-        nj = 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), batch_size, ngpu, model))
-    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"))
-
+    inference_pipeline(audio_in=args.audio_in)

 if __name__ == "__main__":
-    params = {}
-    params["model"] = "damo/speech_paraformer_asr_nat-zh-cn-8k-common-vocab8358-tensorflow1"
-    params["data_dir"] = "./data/test"
-    params["output_dir"] = "./results"
-    params["ngpu"] = 1 # if ngpu > 0, will use gpu decoding
-    params["njob"] = 1 # if ngpu = 0, will use cpu decoding
-    params["batch_size"] = 64
-    modelscope_infer(params)
+    parser = argparse.ArgumentParser()
+    parser.add_argument('--model', type=str, default="damo/speech_paraformer_asr_nat-zh-cn-8k-common-vocab8358-tensorflow1")
+    parser.add_argument('--audio_in', type=str, default="./data/test")
+    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)
--- a/egs_modelscope/asr/paraformer/speech_paraformer_asr_nat-zh-cn-8k-common-vocab8358-tensorflow1/infer.sh
+++ b/egs_modelscope/asr/paraformer/speech_paraformer_asr_nat-zh-cn-8k-common-vocab8358-tensorflow1/infer.sh
@ -0,0 +1,70 @@
+#!/usr/bin/env bash
+
+set -e
+set -u
+set -o pipefail
+
+stage=1
+stop_stage=2
+model="damo/speech_paraformer_asr_nat-zh-cn-8k-common-vocab8358-tensorflow1"
+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=4    # the number of jobs for CPU decoding, if gpu_inference=false, use CPU decoding, please set njob
+
+
+if ${gpu_inference}; then
+    nj=$(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 [ $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 ..."
+    python utils/proce_text.py ${output_dir}/1best_recog/text ${output_dir}/1best_recog/text.proc
+    python utils/proce_text.py ${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
--- a/egs_modelscope/asr/paraformer/speech_paraformer_asr_nat-zh-cn-8k-common-vocab8358-tensorflow1/utils
+++ b/egs_modelscope/asr/paraformer/speech_paraformer_asr_nat-zh-cn-8k-common-vocab8358-tensorflow1/utils
@ -0,0 +1 @@
+../../../../egs/aishell/transformer/utils