From 4cf44a89f808411a0616c8ed92c3afae3d3e371a Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期三, 21 二月 2024 00:43:27 +0800
Subject: [PATCH] bugfix

---
 examples/aishell/conformer/run.sh                             |    7 ++++---
 funasr/train_utils/trainer.py                                 |    2 +-
 examples/aishell/paraformer/run.sh                            |    1 +
 funasr/auto/auto_model.py                                     |    8 ++++----
 examples/industrial_data_pretraining/bicif_paraformer/demo.py |    4 ++--
 examples/aishell/branchformer/run.sh                          |    1 +
 examples/aishell/e_branchformer/run.sh                        |    1 +
 examples/aishell/transformer/run.sh                           |    7 ++++---
 8 files changed, 18 insertions(+), 13 deletions(-)

diff --git a/examples/aishell/branchformer/run.sh b/examples/aishell/branchformer/run.sh
index f4842d0..dba8b96 100755
--- a/examples/aishell/branchformer/run.sh
+++ b/examples/aishell/branchformer/run.sh
@@ -109,6 +109,7 @@
   log_file="${exp_dir}/exp/${model_dir}/train.log.txt.${current_time}"
   echo "log_file: ${log_file}"
 
+  export CUDA_VISIBLE_DEVICES=$CUDA_VISIBLE_DEVICES
   gpu_num=$(echo $CUDA_VISIBLE_DEVICES | awk -F "," '{print NF}')
   torchrun \
   --nnodes 1 \
diff --git a/examples/aishell/conformer/run.sh b/examples/aishell/conformer/run.sh
index ff99f9e..3029cbd 100755
--- a/examples/aishell/conformer/run.sh
+++ b/examples/aishell/conformer/run.sh
@@ -5,7 +5,7 @@
 
 # general configuration
 feats_dir="../DATA" #feature output dictionary
-exp_dir="."
+exp_dir=`pwd`
 lang=zh
 token_type=char
 stage=0
@@ -109,6 +109,7 @@
   log_file="${exp_dir}/exp/${model_dir}/train.log.txt.${current_time}"
   echo "log_file: ${log_file}"
 
+  export CUDA_VISIBLE_DEVICES=$CUDA_VISIBLE_DEVICES
   gpu_num=$(echo $CUDA_VISIBLE_DEVICES | awk -F "," '{print NF}')
   torchrun \
   --nnodes 1 \
@@ -129,7 +130,7 @@
 if [ ${stage} -le 5 ] && [ ${stop_stage} -ge 5 ]; then
   echo "stage 5: Inference"
 
-  if ${inference_device} == "cuda"; then
+  if [ ${inference_device} == "cuda" ]; then
       nj=$(echo $CUDA_VISIBLE_DEVICES | awk -F "," '{print NF}')
   else
       inference_batch_size=1
@@ -170,7 +171,7 @@
           ++input="${_logdir}/keys.${JOB}.scp" \
           ++output_dir="${inference_dir}/${JOB}" \
           ++device="${inference_device}" \
-          ++batch_size="${inference_batch_size}"
+          ++batch_size="${inference_batch_size}" &> ${_logdir}/log.${JOB}.txt
         }&
 
     done
diff --git a/examples/aishell/e_branchformer/run.sh b/examples/aishell/e_branchformer/run.sh
index 0855798..ed765b8 100755
--- a/examples/aishell/e_branchformer/run.sh
+++ b/examples/aishell/e_branchformer/run.sh
@@ -109,6 +109,7 @@
   log_file="${exp_dir}/exp/${model_dir}/train.log.txt.${current_time}"
   echo "log_file: ${log_file}"
 
+  export CUDA_VISIBLE_DEVICES=$CUDA_VISIBLE_DEVICES
   gpu_num=$(echo $CUDA_VISIBLE_DEVICES | awk -F "," '{print NF}')
   torchrun \
   --nnodes 1 \
diff --git a/examples/aishell/paraformer/run.sh b/examples/aishell/paraformer/run.sh
index 80f81b5..d6f1a2c 100755
--- a/examples/aishell/paraformer/run.sh
+++ b/examples/aishell/paraformer/run.sh
@@ -109,6 +109,7 @@
   log_file="${exp_dir}/exp/${model_dir}/train.log.txt.${current_time}"
   echo "log_file: ${log_file}"
 
+  export CUDA_VISIBLE_DEVICES=$CUDA_VISIBLE_DEVICES
   gpu_num=$(echo $CUDA_VISIBLE_DEVICES | awk -F "," '{print NF}')
   torchrun \
   --nnodes 1 \
diff --git a/examples/aishell/transformer/run.sh b/examples/aishell/transformer/run.sh
index da6d4d6..3a02161 100755
--- a/examples/aishell/transformer/run.sh
+++ b/examples/aishell/transformer/run.sh
@@ -109,6 +109,7 @@
   log_file="${exp_dir}/exp/${model_dir}/train.log.txt.${current_time}"
   echo "log_file: ${log_file}"
 
+  export CUDA_VISIBLE_DEVICES=$CUDA_VISIBLE_DEVICES
   gpu_num=$(echo $CUDA_VISIBLE_DEVICES | awk -F "," '{print NF}')
   torchrun \
   --nnodes 1 \
@@ -129,7 +130,7 @@
 if [ ${stage} -le 5 ] && [ ${stop_stage} -ge 5 ]; then
   echo "stage 5: Inference"
 
-  if ${inference_device} == "cuda"; then
+  if [ ${inference_device} == "cuda" ]; then
       nj=$(echo $CUDA_VISIBLE_DEVICES | awk -F "," '{print NF}')
   else
       inference_batch_size=1
@@ -141,7 +142,7 @@
 
   for dset in ${test_sets}; do
 
-    inference_dir="${exp_dir}/exp/${model_dir}/${inference_checkpoint}/${dset}"
+    inference_dir="${exp_dir}/exp/${model_dir}/infer-${inference_checkpoint}/${dset}"
     _logdir="${inference_dir}/logdir"
 
     mkdir -p "${_logdir}"
@@ -154,7 +155,7 @@
     done
     utils/split_scp.pl "${key_file}" ${split_scps}
 
-    gpuid_list_array=(${gpuid_list//,/ })
+    gpuid_list_array=(${CUDA_VISIBLE_DEVICES//,/ })
     for JOB in $(seq ${nj}); do
         {
           id=$((JOB-1))
diff --git a/examples/industrial_data_pretraining/bicif_paraformer/demo.py b/examples/industrial_data_pretraining/bicif_paraformer/demo.py
index 9010200..bb63872 100644
--- a/examples/industrial_data_pretraining/bicif_paraformer/demo.py
+++ b/examples/industrial_data_pretraining/bicif_paraformer/demo.py
@@ -11,8 +11,8 @@
                   vad_model_revision="v2.0.4",
                   punc_model="damo/punc_ct-transformer_zh-cn-common-vocab272727-pytorch",
                   punc_model_revision="v2.0.4",
-                  spk_model="damo/speech_campplus_sv_zh-cn_16k-common",
-                  spk_model_revision="v2.0.4",
+                  # spk_model="damo/speech_campplus_sv_zh-cn_16k-common",
+                  # spk_model_revision="v2.0.2",
                   )
 
 res = model.generate(input="https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_vad_punc_example.wav", batch_size_s=300, batch_size_threshold_s=60)
diff --git a/funasr/auto/auto_model.py b/funasr/auto/auto_model.py
index e95cfd8..e4a154d 100644
--- a/funasr/auto/auto_model.py
+++ b/funasr/auto/auto_model.py
@@ -400,20 +400,20 @@
                     for res, vadsegment in zip(restored_data, vadsegments):
                         sentence_list.append({"start": vadsegment[0],\
                                                 "end": vadsegment[1],
-                                                "sentence": res['raw_text'],
+                                                "sentence": res['text'],
                                                 "timestamp": res['timestamp']})
                 elif self.spk_mode == 'punc_segment':
                     sentence_list = timestamp_sentence(punc_res[0]['punc_array'], \
                                                         result['timestamp'], \
-                                                        result['raw_text'])
+                                                        result['text'])
                 distribute_spk(sentence_list, sv_output)
                 result['sentence_info'] = sentence_list
             elif kwargs.get("sentence_timestamp", False):
                 sentence_list = timestamp_sentence(punc_res[0]['punc_array'], \
                                                         result['timestamp'], \
-                                                        result['raw_text'])
+                                                        result['text'])
                 result['sentence_info'] = sentence_list
-            del result['spk_embedding']
+            if "spk_embedding" in result: del result['spk_embedding']
                     
             result["key"] = key
             results_ret_list.append(result)
diff --git a/funasr/train_utils/trainer.py b/funasr/train_utils/trainer.py
index 129f834..b3c9953 100644
--- a/funasr/train_utils/trainer.py
+++ b/funasr/train_utils/trainer.py
@@ -279,7 +279,7 @@
                     f"epoch: {epoch}/{self.max_epoch}, "
                     f"step: {batch_idx+1}/{len(self.dataloader_train)}, total: {self.batch_total}, "
                     f"(loss: {loss.detach().cpu().item():.3f}), "
-                    f"(lr: {lr}), "
+                    f"(lr: {lr:.3e}), "
                     f"{[(k, round(v.cpu().item(), 3)) for k, v in stats.items()]}, "
                     f"{speed_stats}, "
                     f"{gpu_info}"

--
Gitblit v1.9.1