From 9595a9432fadfbdacd4e6897f6b9a83957699558 Mon Sep 17 00:00:00 2001
From: seanzhang-zhichen <74812416+seanzhang-zhichen@users.noreply.github.com>
Date: 星期二, 05 三月 2024 17:42:14 +0800
Subject: [PATCH] modify paraformer train doc (#1427)
---
/dev/null | 2 -
data/list/val_wav.scp | 0
data/list/train_text.txt | 0
examples/industrial_data_pretraining/paraformer/finetune_from_local.sh | 32 ++++++++++-----
examples/industrial_data_pretraining/paraformer/README_zh.md | 39 +++++++++++++++++++
data/list/train_wav.scp | 0
data/list/val_text.txt | 0
7 files changed, 60 insertions(+), 13 deletions(-)
diff --git a/data/list/audio_datasets.jsonl b/data/list/audio_datasets.jsonl
deleted file mode 100644
index 1c39c76..0000000
--- a/data/list/audio_datasets.jsonl
+++ /dev/null
@@ -1,2 +0,0 @@
-{"key": "ID0012W0013", "prompt": "<ASR>", "source": "/Users/zhifu/funasr_github/test_local/aishell2_dev_ios/wav/D0012/ID0012W0013.wav", "target": "褰撳鎴烽闄╂壙鍙楄兘鍔涜瘎浼颁緷鎹彂鐢熷彉鍖栨椂", "source_len": 454, "target_len": 19}
-{"key":"ID0012W0014", "prompt": "<ASR>", "source": "/Users/zhifu/funasr_github/test_local/aishell2_dev_ios/wav/D0012/ID0012W0014.wav", "target": "鏉ㄦ稕涓嶅緱涓嶅皢宸ュ巶鍏虫帀", "source_len": 211, "target_len": 11}
diff --git a/data/list/text.txt b/data/list/train_text.txt
similarity index 100%
copy from data/list/text.txt
copy to data/list/train_text.txt
diff --git a/data/list/wav.scp b/data/list/train_wav.scp
similarity index 100%
copy from data/list/wav.scp
copy to data/list/train_wav.scp
diff --git a/data/list/text.txt b/data/list/val_text.txt
similarity index 100%
rename from data/list/text.txt
rename to data/list/val_text.txt
diff --git a/data/list/wav.scp b/data/list/val_wav.scp
similarity index 100%
rename from data/list/wav.scp
rename to data/list/val_wav.scp
diff --git a/examples/industrial_data_pretraining/paraformer/README_zh.md b/examples/industrial_data_pretraining/paraformer/README_zh.md
index 8ddb202..f9ab616 100644
--- a/examples/industrial_data_pretraining/paraformer/README_zh.md
+++ b/examples/industrial_data_pretraining/paraformer/README_zh.md
@@ -40,3 +40,42 @@
```[audio_sample1, audio_sample2, ..., audio_sampleN]```
- fbank杈撳叆锛屾敮鎸佺粍batch銆俿hape涓篬batch, frames, dim]锛岀被鍨嬩负torch.Tensor锛屼緥濡�
- `output_dir`: None 锛堥粯璁わ級锛屽鏋滆缃紝杈撳嚭缁撴灉鐨勮緭鍑鸿矾寰�
+
+
+## 寰皟
+
+#### 鍑嗗鏁版嵁
+
+`train_text.txt`
+
+宸﹁竟涓烘暟鎹敮涓�ID锛岄渶涓巂train_wav.scp`涓殑`ID`涓�涓�瀵瑰簲
+鍙宠竟涓洪煶棰戞枃浠舵爣娉ㄦ枃鏈�
+
+```bash
+ID0012W0013 褰撳鎴烽闄╂壙鍙楄兘鍔涜瘎浼颁緷鎹彂鐢熷彉鍖栨椂
+ID0012W0014 鏉ㄦ稕涓嶅緱涓嶅皢宸ュ巶鍏虫帀
+```
+
+
+`train_wav.scp`
+
+宸﹁竟涓烘暟鎹敮涓�ID锛岄渶涓巂train_text.txt`涓殑`ID`涓�涓�瀵瑰簲
+鍙宠竟涓洪煶棰戞枃浠剁殑缁濆璺緞
+
+```bash
+ID0012W0013 /Users/zhifu/funasr_github/test_local/aishell2_dev_ios/wav/D0012/ID0012W0013.wav
+ID0012W0014 /Users/zhifu/funasr_github/test_local/aishell2_dev_ios/wav/D0012/ID0012W0014.wav
+```
+
+#### 璁粌
+
+```bash
+cd examples/industrial_data_pretraining/paraformer
+sh finetune_from_local.sh
+```
+
+**鏌ョ湅璁粌鏃ュ織**
+
+```bash
+tensorboard --logdir /xxxx/FunASR/examples/industrial_data_pretraining/paraformer/outputs/log/tensorboard
+```
\ No newline at end of file
diff --git a/examples/industrial_data_pretraining/paraformer/finetune_from_local.sh b/examples/industrial_data_pretraining/paraformer/finetune_from_local.sh
index 5b4d991..dcbdf77 100644
--- a/examples/industrial_data_pretraining/paraformer/finetune_from_local.sh
+++ b/examples/industrial_data_pretraining/paraformer/finetune_from_local.sh
@@ -5,6 +5,8 @@
workspace=`pwd`
+echo "current path: ${workspace}" # /xxxx/funasr/examples/industrial_data_pretraining/paraformer
+
# download model
local_path_root=${workspace}/modelscope_models
mkdir -p ${local_path_root}
@@ -17,25 +19,32 @@
gpu_num=$(echo $CUDA_VISIBLE_DEVICES | awk -F "," '{print NF}')
# data dir, which contains: train.json, val.json
-data_dir="/Users/zhifu/funasr1.0/data/list"
-
-## generate jsonl from wav.scp and text.txt
-#python -m funasr.datasets.audio_datasets.scp2jsonl \
-#++scp_file_list='["/Users/zhifu/funasr1.0/test_local/wav.scp", "/Users/zhifu/funasr1.0/test_local/text.txt"]' \
-#++data_type_list='["source", "target"]' \
-#++jsonl_file_out=/Users/zhifu/funasr1.0/test_local/audio_datasets.jsonl
+data_dir="../../../data/list"
train_data="${data_dir}/train.jsonl"
val_data="${data_dir}/val.jsonl"
+
+# generate train.jsonl and val.jsonl from wav.scp and text.txt
+python -m funasr.datasets.audio_datasets.scp2jsonl \
+++scp_file_list='["../../../data/list/train_wav.scp", "../../../data/list/train_text.txt"]' \
+++data_type_list='["source", "target"]' \
+++jsonl_file_out="${train_data}"
+
+python -m funasr.datasets.audio_datasets.scp2jsonl \
+++scp_file_list='["../../../data/list/val_wav.scp", "../../../data/list/val_text.txt"]' \
+++data_type_list='["source", "target"]' \
+++jsonl_file_out="${val_data}"
+
+
tokens="${local_path}/tokens.json"
cmvn_file="${local_path}/am.mvn"
-# exp output dir
-output_dir="/Users/zhifu/exp"
+# output dir
+output_dir="./outputs"
log_file="${output_dir}/log.txt"
-config="config.yaml"
+config_name="config.yaml"
init_param="${local_path}/model.pt"
@@ -47,7 +56,7 @@
--nproc_per_node ${gpu_num} \
../../../funasr/bin/train.py \
--config-path "${local_path}" \
---config-name "${config}" \
+--config-name "${config_name}" \
++train_data_set_list="${train_data}" \
++valid_data_set_list="${val_data}" \
++tokenizer_conf.token_list="${tokens}" \
@@ -57,5 +66,6 @@
++dataset_conf.num_workers=4 \
++train_conf.max_epoch=20 \
++optim_conf.lr=0.0002 \
+++train_conf.log_interval=1 \
++init_param="${init_param}" \
++output_dir="${output_dir}" &> ${log_file}
--
Gitblit v1.9.1