update

examples/vm_sound_classification/run.sh

@@ -18,6 +18,9 @@ sh run.sh --stage 3 --stop_stage 3 --system_version windows --file_folder_name f
 sh run.sh --stage 0 --stop_stage 5 --system_version centos --file_folder_name file_dir --final_model_name vm_sound_classification4-ch16 \
 --filename_patterns "/data/tianxing/PycharmProjects/datasets/voicemail/*/wav_finished/*/*.wav" --label_plan 4
 
+sh run.sh --stage 0 --stop_stage 5 --system_version centos --file_folder_name file_dir --final_model_name vm_sound_classification2-ch32 \
+--filename_patterns "/data/tianxing/PycharmProjects/datasets/voicemail/*/wav_finished/*/*.wav" --label_plan 2
+
 "
 
 END

main.py

@@ -10,6 +10,8 @@ import tempfile
 import zipfile
 
 import gradio as gr
+from dill.pointers import parents
+from huggingface_hub import snapshot_download
 import numpy as np
 import torch
 
@@ -34,6 +36,12 @@ def get_args():
         default=environment.get("server_port", 7860),
         type=int
     )
+
+    parser.add_argument(
+        "--models_repo_id",
+        default="qgyd2021/vm_sound_classification",
+        type=str
+    )
     args = parser.parse_args()
     return args
 
@@ -104,6 +112,13 @@ def main():
 
     examples_dir = Path(args.examples_dir)
     trained_model_dir = Path(args.trained_model_dir)
+    trained_model_dir.mkdir(parents=True, exist_ok=True)
+
+    # download models
+    _ = snapshot_download(
+        repo_id=args.models_repo_id,
+        local_dir=trained_model_dir.as_posix()
+    )
 
     # models
     model_choices = list()

requirements.txt

@@ -9,5 +9,5 @@ tqdm==4.66.4
 overrides==1.9.0
 pyyaml==6.0.1
 evaluate==0.4.2
-gradio==4.37.1
+gradio==4.44.1
 python-dotenv==1.0.1