Merge branch 'dev-model-list'

app.py

@@ -3,15 +3,16 @@ import gradio as gr
 # Use a pipeline as a high-level helper
 import torch
 from transformers import AutoModelForSpeechSeq2Seq, AutoProcessor, pipeline
-from datasets import load_dataset
+# from datasets import load_dataset
 
 @spaces.GPU(duration=120)
-def transcribe_audio(audio):
+def transcribe_audio(audio, model_id):
+    if audio is None:
+        return "Please upload an audio file."
+
     device = "cuda:0" if torch.cuda.is_available() else "cpu"
     torch_dtype = torch.float16 if torch.cuda.is_available() else torch.float32
 
-    model_id = "openai/whisper-large-v3"
-
     model = AutoModelForSpeechSeq2Seq.from_pretrained(
         model_id, torch_dtype=torch_dtype, low_cpu_mem_usage=True, use_safetensors=True
     )
@@ -36,7 +37,7 @@ def transcribe_audio(audio):
 
 
 demo = gr.Interface(fn=transcribe_audio,
-                    inputs=gr.Audio(sources="upload", type="filepath"),
+                    inputs=[gr.Audio(sources="upload", type="filepath"), gr.Dropdown(choices=["openai/whisper-large-v3", "alvanlii/whisper-small-cantonese"])],
                     outputs="text")
 demo.launch()