(wip)debug

app.py

@@ -56,6 +56,7 @@ sys.path.append('{}/third_party/Matcha-TTS'.format(ROOT_DIR))
 from huggingface_hub import snapshot_download
 snapshot_download('FunAudioLLM/CosyVoice2-0.5B', local_dir='pretrained_models/CosyVoice2-0.5B')
 snapshot_download('kemuriririn/CosyVoice-ttsfrd', local_dir='pretrained_models/CosyVoice-ttsfrd')
+snapshot_download('FunAudioLLM/SenseVoiceSmall', local_dir='pretrained_models/SenseVoiceSmall')
 os.system('cd pretrained_models/CosyVoice-ttsfrd/ && pip install ttsfrd_dependency-0.1-py3-none-any.whl && pip install ttsfrd-0.4.2-cp310-cp310-linux_x86_64.whl && unzip resource.zip -d .')
 
 from cosyvoice.cli.cosyvoice import CosyVoice2
@@ -95,15 +96,13 @@ def infer_zeroshot(tts_text, prompt_text, prompt_speech_16k, stream, speed):
     for i in cosyvoice.inference_zero_shot(tts_text, prompt_text, prompt_speech_16k, stream=stream, speed=speed):
         yield i
 
-
-@spaces.GPU
 def get_asr():
     global asr_model
     if asr_model is not None:
         return asr_model
     else:
         logging.info('asr model load')
-        model_dir = "FunAudioLLM/SenseVoiceSmall"
+        model_dir = "pretrained_models/SenseVoiceSmall"
         asr_model = AutoModel(
             model=model_dir,
             disable_update=True,