train finetune demo

游雁

2024-02-22 6aba0e3b5689b5b24ba9c56d9947ce1a859b2ad9

train finetune demo

 .gitignore

@@ -24,3 +24,4 @@
outputs*
emotion2vec*
GPT-SoVITS*
modelscope_models

 examples/aishell/paraformer/demo_train_or_finetune.sh

@@ -17,7 +17,7 @@

train_data="${data_dir}/train.jsonl"
val_data="${data_dir}/val.jsonl"
tokens="${data_dir}/tokens.jsonl"
tokens="${data_dir}/tokens.json"
cmvn_file="${data_dir}/am.mvn"

# exp output dir
@@ -45,7 +45,7 @@
++dataset_conf.batch_size=32 \
++dataset_conf.batch_type="example" \
++dataset_conf.num_workers=4 \
++train_conf.max_epoch=20 \
++train_conf.max_epoch=150 \
++optim_conf.lr=0.0002 \
++init_param="${init_param}" \
++output_dir="${output_dir}" &> ${log_file}

 examples/industrial_data_pretraining/paraformer/demo.sh

File was deleted

 examples/industrial_data_pretraining/paraformer/finetune.sh

File was renamed from examples/industrial_data_pretraining/paraformer/finetune_from_model_hub.sh
@@ -1,6 +1,8 @@
# Copyright FunASR (https://github.com/alibaba-damo-academy/FunASR). All Rights Reserved.
#  MIT License  (https://opensource.org/licenses/MIT)

# method1, finetune from model hub

# which gpu to train or finetune
export CUDA_VISIBLE_DEVICES="0,1"
gpu_num=$(echo $CUDA_VISIBLE_DEVICES | awk -F "," '{print NF}')
@@ -30,8 +32,8 @@
--nnodes 1 \
--nproc_per_node ${gpu_num} \
funasr/bin/train.py \
+model="damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch" \
+model_revision="v2.0.4" \
++model="damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch" \
++model_revision="v2.0.4" \
++train_data_set_list="${train_data}" \
++valid_data_set_list="${val_data}" \
++dataset_conf.batch_size=32 \

 examples/industrial_data_pretraining/paraformer/finetune_from_local.sh

File was renamed from examples/industrial_data_pretraining/paraformer/finetune_from_local_model.sh
@@ -1,8 +1,12 @@
# Copyright FunASR (https://github.com/alibaba-damo-academy/FunASR). All Rights Reserved.
#  MIT License  (https://opensource.org/licenses/MIT)

# method2, finetune from local model

workspace=`pwd`

# download model
local_path_root=../modelscope_models
local_path_root=${workspace}/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 ${local_path}
@@ -24,15 +28,14 @@
train_data="${data_dir}/train.jsonl"
val_data="${data_dir}/val.jsonl"

tokens="${local_path}/tokens.jsonl"
tokens="${local_path}/tokens.json"
cmvn_file="${local_path}/am.mvn"

# exp output dir
output_dir="/Users/zhifu/exp"
log_file="${output_dir}/log.txt"

workspace=`pwd`
config="${local_path}/config.yaml"
config="config.yaml"

init_param="${local_path}/model.pt"

@@ -43,7 +46,7 @@
--nnodes 1 \
--nproc_per_node ${gpu_num} \
../../../funasr/bin/train.py \
--config-path "${workspace}/conf" \
--config-path "${local_path}" \
--config-name "${config}" \
++train_data_set_list="${train_data}" \
++valid_data_set_list="${val_data}" \

 examples/industrial_data_pretraining/paraformer/infer.sh

New file
@@ -0,0 +1,21 @@
# Copyright FunASR (https://github.com/alibaba-damo-academy/FunASR). All Rights Reserved.
#  MIT License  (https://opensource.org/licenses/MIT)

# method1, inference from model hub

# for more input type, please ref to readme.md
input="https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav"

output_dir="./outputs/debug"

model="damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch"
model_revision="v2.0.4"

device="cuda:0" # "cuda:0" for gpu0, "cuda:1" for gpu1, "cpu"

python -m funasr.bin.inference \
++model=${model} \
++model_revision=${model_revision} \
++input="${input}" \
++output_dir="${output_dir}" \
++device="${device}" \

 examples/industrial_data_pretraining/paraformer/infer_from_local.sh

New file
@@ -0,0 +1,39 @@
# Copyright FunASR (https://github.com/alibaba-damo-academy/FunASR). All Rights Reserved.
#  MIT License  (https://opensource.org/licenses/MIT)

# method2, inference from local model

# for more input type, please ref to readme.md
input="https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav"

output_dir="./outputs/debug"

workspace=`pwd`

# download model
local_path_root=${workspace}/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}

device="cuda:0" # "cuda:0" for gpu0, "cuda:1" for gpu1, "cpu"

tokens="${local_path}/tokens.json"
cmvn_file="${local_path}/am.mvn"

config="config.yaml"
init_param="${local_path}/model.pt"

python -m funasr.bin.inference \
--config-path "${local_path}" \
--config-name "${config}" \
++init_param="${init_param}" \
++tokenizer_conf.token_list="${tokens}" \
++frontend_conf.cmvn_file="${cmvn_file}" \
++input="${input}" \
++output_dir="${output_dir}" \
++device="${device}" \