Update app.py

app.py

@@ -13,7 +13,7 @@ from nemo.collections.asr.models import ASRModel
 from nemo.collections.asr.parts.utils.streaming_utils import FrameBatchMultiTaskAED
 from nemo.collections.asr.parts.utils.transcribe_utils import get_buffered_pred_feat_multitaskAED
 
-
+available_memory()
 
 torch.random.manual_seed(0)
 proc_model_name = "microsoft/Phi-3-mini-4k-instruct"
@@ -27,6 +27,7 @@ proc_model = AutoModelForCausalLM.from_pretrained(
 proc_model.to("cpu")
 proc_tokenizer = AutoTokenizer.from_pretrained(proc_model_name)
 
+available_memory()
 
 SAMPLE_RATE = 16000 # Hz
 MAX_AUDIO_MINUTES = 10 # wont try to transcribe if longer than this
@@ -116,8 +117,8 @@ def generate_response(user_input):
     
 def CanaryPhi(audio_filepath):
     user_input = transcribe(audio_filepath)
-    #response = generate_response(user_input)
-    response = llama_pipe(user_input)
+    print(user_input)
+    response = generate_response(user_input)
     return response