Update app.py

app.py

@@ -2,30 +2,6 @@ import gradio as gr
 from transformers import pipeline
 import librosa
 
-
-########################ASR model###############################
-
-from transformers import WhisperProcessor, WhisperForConditionalGeneration
-
-# load model and processor
-processor = WhisperProcessor.from_pretrained("openai/whisper-base")
-model = WhisperForConditionalGeneration.from_pretrained("openai/whisper-base")
-model.config.forced_decoder_ids = None
-
-sample_rate = 16000
-
-def ASR_model(audio, sr=16000):
-    DB_audio = audio
-    input_features = processor(audio, sampling_rate=sr, return_tensors="pt").input_features
-    # generate token ids
-    predicted_ids = model.generate(input_features)
-    # decode token ids to text
-    transcription = processor.batch_decode(predicted_ids, skip_special_tokens=False)
-
-    transcription = processor.batch_decode(predicted_ids, skip_special_tokens=True)
-
-    return transcription
-
 ########################LLama model###############################
 from transformers import AutoModelForCausalLM, AutoTokenizer
 
@@ -69,6 +45,31 @@ def RallyRespone(chat_history, message):
     res = t_chat[t_chat.rfind("Rally: "):]
     return res
 
+########################ASR model###############################
+
+from transformers import WhisperProcessor, WhisperForConditionalGeneration
+
+# load model and processor
+processor = WhisperProcessor.from_pretrained("openai/whisper-base")
+model = WhisperForConditionalGeneration.from_pretrained("openai/whisper-base")
+model.config.forced_decoder_ids = None
+
+sample_rate = 16000
+
+def ASR_model(audio, sr=16000):
+    DB_audio = audio
+    input_features = processor(audio, sampling_rate=sr, return_tensors="pt").input_features
+    # generate token ids
+    predicted_ids = model.generate(input_features)
+    # decode token ids to text
+    transcription = processor.batch_decode(predicted_ids, skip_special_tokens=False)
+
+    transcription = processor.batch_decode(predicted_ids, skip_special_tokens=True)
+
+    return transcription
+
+
+
 ########################Gradio UI###############################
     
 # Chatbot demo with multimodal input (text, markdown, LaTeX, code blocks, image, audio, & video). Plus shows support for streaming text.