From 2ed3f46f40cd5da19cad76a97b52c46b2869d5ed Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期二, 16 一月 2024 18:42:37 +0800
Subject: [PATCH] funasr1.0 finetune
---
examples/industrial_data_pretraining/paraformer/finetune.sh | 21 ++++++++++++---------
1 files changed, 12 insertions(+), 9 deletions(-)
diff --git a/examples/industrial_data_pretraining/paraformer/finetune.sh b/examples/industrial_data_pretraining/paraformer/finetune.sh
index 6dca09f..93cce73 100644
--- a/examples/industrial_data_pretraining/paraformer/finetune.sh
+++ b/examples/industrial_data_pretraining/paraformer/finetune.sh
@@ -1,14 +1,17 @@
-# 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}
+## 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}
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" \
++model="damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch" \
++model_revision="v2.0.2" \
++train_data_set_list="/Users/zhifu/funasr_github/test_local/aishell2_dev_ios/asr_task_debug_len.jsonl" \
+++dataset_conf.batch_size=2 \
+++dataset_conf.batch_type="example" \
+output_dir="outputs/debug/ckpt/funasr2/exp2" \
-+device="cpu"
\ No newline at end of file
++device="cpu" \
++debug="true"
\ No newline at end of file
--
Gitblit v1.9.1