diff --git a/data/train_example.jsonl b/data/train_example.jsonl
new file mode 100644
index 0000000..d6e6daa
--- /dev/null
+++ b/data/train_example.jsonl
@@ -0,0 +1 @@
+{"messages": [{"role": "system", "content": "You are a helpful assistant."}, {"role": "user", "content": "语音转写：<|startofspeech|>!/path/to/wav<|endofspeech|>"}, {"role": "assistant", "content": "content of /path/to/wav"}], "speech_length": 42, "text_length": 42}
diff --git a/data/val_example.jsonl b/data/val_example.jsonl
new file mode 100644
index 0000000..d6e6daa
--- /dev/null
+++ b/data/val_example.jsonl
@@ -0,0 +1 @@
+{"messages": [{"role": "system", "content": "You are a helpful assistant."}, {"role": "user", "content": "语音转写：<|startofspeech|>!/path/to/wav<|endofspeech|>"}, {"role": "assistant", "content": "content of /path/to/wav"}], "speech_length": 42, "text_length": 42}
diff --git a/deepspeed_conf/ds_stage1.json b/deepspeed_conf/ds_stage1.json
new file mode 100644
index 0000000..51804c1
--- /dev/null
+++ b/deepspeed_conf/ds_stage1.json
@@ -0,0 +1,33 @@
+{
+  "train_micro_batch_size_per_gpu": 1,
+  "gradient_accumulation_steps": 1,
+  "steps_per_print": 100,
+  "gradient_clipping": 5,
+  "fp16": {
+    "enabled": false,
+    "auto_cast": false,
+    "loss_scale": 0,
+    "initial_scale_power": 16,
+    "loss_scale_window": 1000,
+    "hysteresis": 2,
+    "consecutive_hysteresis": false,
+    "min_loss_scale": 1
+  },
+  "bf16": {
+   "enabled": true
+  },
+  "zero_force_ds_cpu_optimizer": false,
+  "zero_optimization": {
+    "stage": 1,
+    "offload_optimizer": {
+      "device": "none",
+      "pin_memory": true
+    },
+    "allgather_partitions": true,
+    "allgather_bucket_size": 5e8,
+    "overlap_comm": true,
+    "reduce_scatter": true,
+    "reduce_bucket_size": 5e8,
+    "contiguous_gradients" : true
+  }
+}
diff --git a/finetune.sh b/finetune.sh
new file mode 100644
index 0000000..219d9b4
--- /dev/null
+++ b/finetune.sh
@@ -0,0 +1,80 @@
+# Copyright FunASR (https://github.com/alibaba-damo-academy/FunASR). All Rights Reserved.
+#  MIT License  (https://opensource.org/licenses/MIT)
+
+workspace=`pwd`
+
+# which gpu to train or finetune
+export CUDA_VISIBLE_DEVICES="0"
+gpu_num=$(echo $CUDA_VISIBLE_DEVICES | awk -F "," '{print NF}')
+
+# model_name from model_hub, or model_dir in local path
+
+## option 1, download model automatically
+model_name_or_model_dir="FunAudioLLM/Fun-ASR-Nano-2512"
+
+## option 2, download model by git
+#local_path_root=${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
+train_data=${workspace}/data/train_example.jsonl
+val_data=${workspace}/data/val_example.jsonl
+
+# exp output dir
+output_dir="./outputs"
+log_file="${output_dir}/log.txt"
+
+deepspeed_config=${workspace}/deepspeed_conf/ds_stage1.json
+
+mkdir -p ${output_dir}
+echo "log_file: ${log_file}"
+
+DISTRIBUTED_ARGS="
+    --nnodes ${WORLD_SIZE:-1} \
+    --nproc_per_node $gpu_num \
+    --node_rank ${RANK:-0} \
+    --master_addr ${MASTER_ADDR:-127.0.0.1} \
+    --master_port ${MASTER_PORT:-26669}
+"
+
+echo $DISTRIBUTED_ARGS
+
+# funasr trainer path
+if [ -f `dirname $(which funasr)`/train_ds.py ]; then
+    train_tool=`dirname $(which funasr)`/train_ds.py
+elif [ -f `dirname $(which funasr)`/../lib/python*/site-packages/funasr/bin/train_ds.py ]; then
+    train_tool=`dirname $(which funasr)`/../lib/python*/site-packages/funasr/bin/train_ds.py
+else
+    echo "Error: train_ds.py not found in funasr bin directory."
+    exit 1
+fi
+ABSOLUTE_PATH=$(cd $(dirname $train_tool); pwd)
+train_tool=${ABSOLUTE_PATH}/train_ds.py
+echo "Using funasr trainer: ${train_tool}"
+
+torchrun $DISTRIBUTED_ARGS \
+${train_tool} \
+++model="${model_name_or_model_dir}" \
+++trust_remote_code=true \
+++train_data_set_list="${train_data}" \
+++valid_data_set_list="${val_data}" \
+++dataset_conf.data_split_num=1 \
+++dataset_conf.batch_sampler="BatchSampler" \
+++dataset_conf.batch_size=6000  \
+++dataset_conf.sort_size=1024 \
+++dataset_conf.batch_type="token" \
+++dataset_conf.num_workers=4 \
+++train_conf.max_epoch=50 \
+++train_conf.log_interval=1 \
+++train_conf.resume=true \
+++train_conf.validate_interval=2000 \
+++train_conf.save_checkpoint_interval=2000 \
+++train_conf.keep_nbest_models=20 \
+++train_conf.avg_nbest_model=10 \
+++train_conf.use_deepspeed=false \
+++train_conf.deepspeed_config=${deepspeed_config} \
+++optim_conf.lr=0.0002 \
+++output_dir="${output_dir}" &> ${log_file}
diff --git a/model.py b/model.py
index ea6b6c3..657edcc 100644
--- a/model.py
+++ b/model.py
@@ -125,7 +125,6 @@ class FunASRNano(nn.Module):
         self.use_low_frame_rate = audio_adaptor_conf.get("use_low_frame_rate", False)
 
         self.length_normalized_loss = length_normalized_loss
-        self.feat_permute = audio_encoder_conf.get("feat_permute", True)
         rank = int(os.environ.get("RANK", 0))
         logging.info(f"rank: {rank}, model is builded.")
 
@@ -255,12 +254,7 @@ class FunASRNano(nn.Module):
 
     def encode(self, speech, speech_lengths):
         # audio encoder
-        if self.feat_permute:
-            encoder_out, encoder_out_lens = self.audio_encoder(
-                speech.permute(0, 2, 1), speech_lengths
-            )
-        else:
-            encoder_out, encoder_out_lens = self.audio_encoder(speech, speech_lengths)
+        encoder_out, encoder_out_lens = self.audio_encoder(speech, speech_lengths)
 
         return encoder_out, encoder_out_lens
 
@@ -385,9 +379,6 @@ class FunASRNano(nn.Module):
                             / 1000
                         )
 
-                        if self.feat_permute:
-                            speech = speech.permute(0, 2, 1)
-
                         if self.use_low_frame_rate:
                             olens = 1 + (speech_lengths[0].item() - 3 + 2 * 1) // 2
                             olens = 1 + (olens - 3 + 2 * 1) // 2