From 610b3b35e48300fe7e9da90c6ef9e2c174c9ed00 Mon Sep 17 00:00:00 2001
From: 九耳 <mengzhe.cmz@alibaba-inc.com>
Date: 星期四, 27 四月 2023 17:52:10 +0800
Subject: [PATCH] template
---
egs_modelscope/punctuation/TEMPLATE/infer.sh | 66 ++++++++++++++++
egs_modelscope/punctuation/TEMPLATE/README.md | 112 ++++++++++++++++++++++++++++
egs_modelscope/punctuation/TEMPLATE/infer.py | 23 +++++
egs_modelscope/punctuation/TEMPLATE/utils | 1
4 files changed, 202 insertions(+), 0 deletions(-)
diff --git a/egs_modelscope/punctuation/TEMPLATE/README.md b/egs_modelscope/punctuation/TEMPLATE/README.md
new file mode 100644
index 0000000..5618973
--- /dev/null
+++ b/egs_modelscope/punctuation/TEMPLATE/README.md
@@ -0,0 +1,112 @@
+# Punctuation Restoration
+# Voice Activity Detection
+
+> **Note**:
+> The modelscope pipeline supports all the models in [model zoo](https://alibaba-damo-academy.github.io/FunASR/en/modelscope_models.html#pretrained-models-on-modelscope) to inference and finetune. Here we take the model of the punctuation model of CT-Transformer as example to demonstrate the usage.
+
+## Inference
+
+### Quick start
+#### [CT-Transformer model](https://www.modelscope.cn/models/damo/punc_ct-transformer_zh-cn-common-vocab272727-pytorch/summary)
+```python
+from modelscope.pipelines import pipeline
+from modelscope.utils.constant import Tasks
+
+inference_pipline = pipeline(
+ task=Tasks.punctuation,
+ model='damo/punc_ct-transformer_zh-cn-common-vocab272727-pytorch',
+ model_revision=None)
+
+rec_result = inference_pipline(text_in='example/punc_example.txt')
+print(rec_result)
+```
+- text浜岃繘鍒舵暟鎹紝渚嬪锛氱敤鎴风洿鎺ヤ粠鏂囦欢閲岃鍑篵ytes鏁版嵁
+```python
+rec_result = inference_pipline(text_in='鎴戜滑閮芥槸鏈ㄥご浜轰笉浼氳璇濅笉浼氬姩')
+```
+- text鏂囦欢url锛屼緥濡傦細https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_text/punc_example.txt
+```python
+rec_result = inference_pipline(text_in='https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_text/punc_example.txt')
+```
+
+#### [CT-Transformer Realtime model](https://www.modelscope.cn/models/damo/punc_ct-transformer_zh-cn-common-vad_realtime-vocab272727/summary)
+```python
+from modelscope.pipelines import pipeline
+from modelscope.utils.constant import Tasks
+
+inference_pipeline = pipeline(
+ task=Tasks.punctuation,
+ model='damo/punc_ct-transformer_zh-cn-common-vad_realtime-vocab272727',
+ model_revision=None,
+)
+
+inputs = "璺ㄥ娌虫祦鏄吇鑲叉部宀竱浜烘皯鐨勭敓鍛戒箣婧愰暱鏈熶互鏉ヤ负甯姪涓嬫父鍦板尯闃茬伨鍑忕伨涓柟鎶�鏈汉鍛榺鍦ㄤ笂娓稿湴鍖烘瀬涓烘伓鍔ｇ殑鑷劧鏉′欢涓嬪厠鏈嶅法澶у洶闅剧敋鑷冲啋鐫�鐢熷懡鍗遍櫓|鍚戝嵃鏂规彁渚涙睕鏈熸按鏂囪祫鏂欏鐞嗙揣鎬ヤ簨浠朵腑鏂归噸瑙嗗嵃鏂瑰湪璺ㄥ娌虫祦闂涓婄殑鍏冲垏|鎰挎剰杩涗竴姝ュ畬鍠勫弻鏂硅仈鍚堝伐浣滄満鍒秥鍑℃槸|涓柟鑳藉仛鐨勬垜浠瑋閮戒細鍘诲仛鑰屼笖浼氬仛寰楁洿濂芥垜璇峰嵃搴︽湅鍙嬩滑鏀惧績涓浗鍦ㄤ笂娓哥殑|浠讳綍寮�鍙戝埄鐢ㄩ兘浼氱粡杩囩瀛瑙勫垝鍜岃璇佸吋椤句笂涓嬫父鐨勫埄鐩�"
+vads = inputs.split("|")
+rec_result_all="outputs:"
+param_dict = {"cache": []}
+for vad in vads:
+ rec_result = inference_pipeline(text_in=vad, param_dict=param_dict)
+ rec_result_all += rec_result['text']
+
+print(rec_result_all)
+```
+Full code of demo, please ref to [demo](https://github.com/alibaba-damo-academy/FunASR/discussions/238)
+
+
+#### API-reference
+##### Define pipeline
+- `task`: `Tasks.punctuation`
+- `model`: model name in [model zoo](https://alibaba-damo-academy.github.io/FunASR/en/modelscope_models.html#pretrained-models-on-modelscope), or model path in local disk
+- `ngpu`: `1` (Default), decoding on GPU. If ngpu=0, decoding on CPU
+- `output_dir`: `None` (Default), the output path of results if set
+- `model_revision`: `None` (Default), setting the model version
+
+##### Infer pipeline
+- `text_in`: the input to decode, which could be:
+ - text bytes, `e.g.`: "鎴戜滑閮芥槸鏈ㄥご浜轰笉浼氳璇濅笉浼氬姩"
+ - text file, `e.g.`: example/punc_example.txt
+ In this case of `text file` input, `output_dir` must be set to save the output results
+- `param_dict`: reserving the cache which is necessary in realtime mode.
+
+### Inference with multi-thread CPUs or multi GPUs
+FunASR also offer recipes [egs_modelscope/punc/TEMPLATE/infer.sh](https://github.com/alibaba-damo-academy/FunASR/blob/main/egs_modelscope/punc/TEMPLATE/infer.sh) to decode with multi-thread CPUs, or multi GPUs. It is an offline recipe and only support offline model.
+
+- Setting parameters in `infer.sh`
+ - `model`: model name in [model zoo](https://alibaba-damo-academy.github.io/FunASR/en/modelscope_models.html#pretrained-models-on-modelscope), or model path in local disk
+ - `data_dir`: the dataset dir needs to include `punc.txt`
+ - `output_dir`: output dir of the recognition results
+ - `gpu_inference`: `true` (Default), whether to perform gpu decoding, set false for CPU inference
+ - `gpuid_list`: `0,1` (Default), which gpu_ids are used to infer
+ - `njob`: only used for CPU inference (`gpu_inference`=`false`), `64` (Default), the number of jobs for CPU decoding
+ - `checkpoint_dir`: only used for infer finetuned models, the path dir of finetuned models
+ - `checkpoint_name`: only used for infer finetuned models, `punc.pb` (Default), which checkpoint is used to infer
+
+- Decode with multi GPUs:
+```shell
+ bash infer.sh \
+ --model "damo/punc_ct-transformer_zh-cn-common-vocab272727-pytorch" \
+ --data_dir "./data/test" \
+ --output_dir "./results" \
+ --batch_size 64 \
+ --gpu_inference true \
+ --gpuid_list "0,1"
+```
+- Decode with multi-thread CPUs:
+```shell
+ bash infer.sh \
+ --model "damo/punc_ct-transformer_zh-cn-common-vocab272727-pytorch" \
+ --data_dir "./data/test" \
+ --output_dir "./results" \
+ --gpu_inference false \
+ --njob 64
+```
+
+
+## Finetune with pipeline
+
+### Quick start
+
+### Finetune with your data
+
+## Inference with your finetuned model
+
diff --git a/egs_modelscope/punctuation/TEMPLATE/infer.py b/egs_modelscope/punctuation/TEMPLATE/infer.py
new file mode 100644
index 0000000..edcefbe
--- /dev/null
+++ b/egs_modelscope/punctuation/TEMPLATE/infer.py
@@ -0,0 +1,23 @@
+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.punctuation,
+ model=args.model,
+ output_dir=args.output_dir,
+ )
+ inference_pipeline(text_in=args.text_in)
+
+if __name__ == "__main__":
+ parser = argparse.ArgumentParser()
+ parser.add_argument('--model', type=str, default="damo/punc_ct-transformer_zh-cn-common-vocab272727-pytorch")
+ parser.add_argument('--text_in', type=str, default="./data/test/punc.txt")
+ parser.add_argument('--output_dir', type=str, default="./results/")
+ 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/punctuation/TEMPLATE/infer.sh b/egs_modelscope/punctuation/TEMPLATE/infer.sh
new file mode 100644
index 0000000..9f3e6c2
--- /dev/null
+++ b/egs_modelscope/punctuation/TEMPLATE/infer.sh
@@ -0,0 +1,66 @@
+#!/usr/bin/env bash
+
+set -e
+set -u
+set -o pipefail
+
+stage=1
+stop_stage=2
+model="damo/punc_ct-transformer_zh-cn-common-vocab272727-pytorch"
+data_dir="./data/test"
+output_dir="./results"
+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="punc.pb"
+
+. utils/parse_options.sh || exit 1;
+
+if ${gpu_inference} == "true"; then
+ nj=$(echo $gpuid_list | awk -F "," '{print NF}')
+else
+ nj=$njob
+ 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 $output_dir/split/text.$JOB.scp"
+done
+perl utils/split_scp.pl ${data_dir}/punc.txt ${split_scps}
+
+if [ -n "${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} \
+ --text_in ${output_dir}/split/text.$JOB.scp \
+ --output_dir ${output_dir}/output.$JOB \
+ --gpuid ${gpuid}
+ }&
+ done
+ wait
+
+ mkdir -p ${output_dir}/final_res
+ if [ -f "${output_dir}/output.1/output.res" ]; then
+ for i in $(seq "${nj}"); do
+ cat "${output_dir}/output.${i}/output.res"
+ done | sort -k1 >"${output_dir}/output.res"
+ fi
+fi
+
diff --git a/egs_modelscope/punctuation/TEMPLATE/utils b/egs_modelscope/punctuation/TEMPLATE/utils
new file mode 120000
index 0000000..dc7d417
--- /dev/null
+++ b/egs_modelscope/punctuation/TEMPLATE/utils
@@ -0,0 +1 @@
+../../../egs/aishell/transformer/utils
\ No newline at end of file
--
Gitblit v1.9.1