Update app.py

app.py

@@ -1,7 +1,9 @@
 import gradio as gr
 # from transformers import WhisperProcessor, WhisperForConditionalGeneration
 from datasets import load_dataset
-from transformers import AutoModelForSpeechSeq2Seq, AutoProcessor, pipeline
+# from transformers import AutoModelForSpeechSeq2Seq, AutoProcessor, pipeline,WhisperProcessor
+from transformers import WhisperProcessor, WhisperForConditionalGeneration
+
 
 import torch
 # import librosa
@@ -11,17 +13,20 @@ import torch
 # processor = WhisperProcessor.from_pretrained(model_name)
 # model = WhisperForConditionalGeneration.from_pretrained(model_name)
 
-model_id = "openai/whisper-large-v3-turbo"
+model_name = "openai/whisper-large-v3-turbo"
 
-models = AutoModelForSpeechSeq2Seq.from_pretrained(
-    model_id,  low_cpu_mem_usage=True
-)
+# models = AutoModelForSpeechSeq2Seq.from_pretrained(
+#     model_id,  low_cpu_mem_usage=True
+# )
+
+processor = WhisperProcessor.from_pretrained(model_name)
+model = WhisperForConditionalGeneration.from_pretrained(model_name)
 
-model = pipeline("automatic-speech-recognition", model=models, chunk_length_s=30, device=0)
+# model = pipeline("automatic-speech-recognition", model=models, chunk_length_s=30, device=0)
 
 # 加载数据集 bigcode/the-stack
 
-# ds = load_dataset("CoIR-Retrieval/CodeSearchNet-php-queries-corpus")
+ds = load_dataset("CoIR-Retrieval/CodeSearchNet-php-queries-corpus")
 
 def transcribe(audio_path):
     # 加载音频文件并转换为信号