From e9d2cfc3a134b00f4e98271fbee3838d1ccecbcc Mon Sep 17 00:00:00 2001
From: VirtuosoQ <2416050435@qq.com>
Date: 星期五, 26 四月 2024 14:59:30 +0800
Subject: [PATCH] FunASR java http  client

---
 examples/industrial_data_pretraining/paraformer/finetune.sh |   76 ++++++++++++++++++++++++++++++++------
 1 files changed, 64 insertions(+), 12 deletions(-)

diff --git a/examples/industrial_data_pretraining/paraformer/finetune.sh b/examples/industrial_data_pretraining/paraformer/finetune.sh
index 6dca09f..9467a0b 100644
--- a/examples/industrial_data_pretraining/paraformer/finetune.sh
+++ b/examples/industrial_data_pretraining/paraformer/finetune.sh
@@ -1,14 +1,66 @@
-
-# download model
-local_path_root=../modelscope_models
-mkdir -p ${local_path_root}
-local_path=${local_path_root}/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch
-git clone https://www.modelscope.cn/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch.git ${local_path}
+# Copyright FunASR (https://github.com/alibaba-damo-academy/FunASR). All Rights Reserved.
+#  MIT License  (https://opensource.org/licenses/MIT)
 
 
-python funasr/bin/train.py \
-+model="../modelscope_models/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch" \
-+token_list="../modelscope_models/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/tokens.txt" \
-+train_data_set_list="data/list/audio_datasets.jsonl" \
-+output_dir="outputs/debug/ckpt/funasr2/exp2" \
-+device="cpu"
\ No newline at end of file
+# which gpu to train or finetune
+export CUDA_VISIBLE_DEVICES="0,1"
+gpu_num=$(echo $CUDA_VISIBLE_DEVICES | awk -F "," '{print NF}')
+
+# model_name from model_hub, or model_dir in local path
+
+## option 1, download model automatically
+model_name_or_model_dir="iic/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch"
+
+## option 2, download model by git
+#local_path_root=${workspace}/modelscope_models
+#mkdir -p ${local_path_root}/${model_name_or_model_dir}
+#git clone https://www.modelscope.cn/${model_name_or_model_dir}.git ${local_path_root}/${model_name_or_model_dir}
+#model_name_or_model_dir=${local_path_root}/${model_name_or_model_dir}
+
+
+# data dir, which contains: train.json, val.json
+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
+scp2jsonl \
+++scp_file_list='["../../../data/list/train_wav.scp", "../../../data/list/train_text.txt"]' \
+++data_type_list='["source", "target"]' \
+++jsonl_file_out="${train_data}"
+
+scp2jsonl \
+++scp_file_list='["../../../data/list/val_wav.scp", "../../../data/list/val_text.txt"]' \
+++data_type_list='["source", "target"]' \
+++jsonl_file_out="${val_data}"
+
+
+# exp output dir
+output_dir="./outputs"
+log_file="${output_dir}/log.txt"
+
+
+mkdir -p ${output_dir}
+echo "log_file: ${log_file}"
+
+torchrun \
+--nnodes 1 \
+--node_rank 0 \
+--nproc_per_node ${gpu_num} \
+../../../funasr/bin/train.py \
+++model="${model_name_or_model_dir}" \
+++train_data_set_list="${train_data}" \
+++valid_data_set_list="${val_data}" \
+++dataset_conf.batch_size=20000 \
+++dataset_conf.batch_type="token" \
+++dataset_conf.num_workers=4 \
+++train_conf.max_epoch=50 \
+++train_conf.log_interval=1 \
+++train_conf.resume=false \
+++train_conf.validate_interval=2000 \
+++train_conf.save_checkpoint_interval=2000 \
+++train_conf.keep_nbest_models=20 \
+++train_conf.avg_nbest_model=10 \
+++optim_conf.lr=0.0002 \
+++output_dir="${output_dir}" &> ${log_file}
\ No newline at end of file

--
Gitblit v1.9.1