Update app.py

app.py

@@ -9,7 +9,10 @@ processor = WhisperProcessor.from_pretrained(model_name)
 model = WhisperForConditionalGeneration.from_pretrained(model_name)
 
 # 加载数据集 bigcode/the-stack
-dataset = load_dataset("CoIR-Retrieval/CodeSearchNet-php-queries-corpus", data_dir="data", split="train[:80%]")
+# dataset = load_dataset("CoIR-Retrieval/CodeSearchNet-php-queries-corpus", data_dir="data", split="train[:80%]")
+queries_dataset = load_dataset("CoIR-Retrieval/CodeSearchNet-php-queries-corpus", data_dir="data", split="queries")
+corpus_dataset = load_dataset("CoIR-Retrieval/CodeSearchNet-php-queries-corpus", data_dir="data", split="corpus")
+
 
 def transcribe(audio):
     # 处理音频进行转录