From a0879e4663a0bcb6e6cdb7f532cde5dc37d54848 Mon Sep 17 00:00:00 2001
From: 北念 <lzr265946@alibaba-inc.com>
Date: 星期三, 22 三月 2023 19:27:15 +0800
Subject: [PATCH] update paraformer recipe
---
egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/infer.sh | 8 +-
egs_modelscope/asr/paraformer/speech_paraformer_asr_nat-zh-cn-8k-common-vocab8358-tensorflow1/README.md | 38 ++++++++-
egs_modelscope/asr/paraformer/speech_paraformer_asr_nat-zh-cn-8k-common-vocab8358-tensorflow1/infer.sh | 70 +++++++++++++++++
egs_modelscope/asr/paraformer/speech_paraformer_asr_nat-zh-cn-8k-common-vocab8358-tensorflow1/utils | 1
egs_modelscope/asr/paraformer/speech_paraformer_asr_nat-zh-cn-8k-common-vocab8358-tensorflow1/infer.py | 108 ++++-----------------------
egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/infer.py | 2
6 files changed, 125 insertions(+), 102 deletions(-)
diff --git 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
index 1973191..6726a41 100644
--- 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 @@
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)
diff --git 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
index ab64849..f080257 100644
--- 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 @@
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 @@
./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 @@
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
diff --git 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
index 1587d3d..8bf63e5 100644
--- 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.
diff --git 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
index 0b508fb..b4f633a 100644
--- 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)
\ No newline at end of file
+ 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)
\ No newline at end of file
diff --git 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
new file mode 100644
index 0000000..cdf81dc
--- /dev/null
+++ 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
diff --git 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
new file mode 120000
index 0000000..2ac163f
--- /dev/null
+++ b/egs_modelscope/asr/paraformer/speech_paraformer_asr_nat-zh-cn-8k-common-vocab8358-tensorflow1/utils
@@ -0,0 +1 @@
+../../../../egs/aishell/transformer/utils
\ No newline at end of file
--
Gitblit v1.9.1