Update app.py

app.py

@@ -7,7 +7,7 @@ import soundfile as sf
 import tempfile
 import uuid
 import torch
-from transformers import AutoTokenizer, VitsModel, set_seed, PhiForCausalLM, AutoTokenizer, pipeline
+from transformers import AutoTokenizer, VitsModel, set_seed, AutoModelForCausalLM, AutoTokenizer, pipeline
 
 from nemo.collections.asr.models import ASRModel
 from nemo.collections.asr.parts.utils.streaming_utils import FrameBatchMultiTaskAED
@@ -16,8 +16,8 @@ from nemo.collections.asr.parts.utils.transcribe_utils import get_buffered_pred_
 
 
 torch.random.manual_seed(0)
-proc_model_name = "SanctumAI/Phi-3-mini-4k-instruct-GGUF"
-proc_model = PhiForCausalLM.from_pretrained(proc_model_name)
+proc_model_name = "SanctumAI/Phi-3-mini-4k-instruct-GGUF/phi-3-mini-4k-instruct.Q6_K.gguf"
+proc_model = AutoModelForCausalLM.from_pretrained(proc_model_name)
 proc_model.to("cpu")
 proc_tokenizer = AutoTokenizer.from_pretrained(proc_model_name)