Update app.py

app.py

@@ -6,9 +6,9 @@ import time
 
 pipe_base = pipeline("automatic-speech-recognition", model="aitor-medrano/lara-base-pushed")
 pipe_small = pipeline("automatic-speech-recognition", model="aitor-medrano/whisper-small-lara")
+pipe_base_2000 = pipeline("automatic-speech-recognition", model="aitor-medrano/whisper-base-lara-2000")
 
-def greet(grabacion, modelo="base"):
-
+def greet(grabacion):
     inicio = time.time()
 
     sr, y = grabacion
@@ -16,26 +16,22 @@ def greet(grabacion, modelo="base"):
     y = y.astype(np.float32)
     y /= np.max(np.abs(y))
 
-    if modelo is not None and modelo == "base":
-        pipe = pipe_base
-    else:
-        modelo = "small"
-        pipe = pipe_small
+    result_base = "base:" + pipe_base({"sampling_rate": sr, "raw": y})["text"]
+    result_small = "small:" + pipe_small({"sampling_rate": sr, "raw": y})["text"]
+    result_base_2000 = "base_2000:" + pipe_base_2000({"sampling_rate": sr, "raw": y})["text"]
 
-    result = modelo + ":" + pipe({"sampling_rate": sr, "raw": y})["text"]
     fin = time.time()
 
-    return result, fin - inicio
+    return result_base, result_small, result_base_2000, fin - inicio
 
 demo = gr.Interface(fn=greet,
         inputs=[
                 gr.Audio(),
-                gr.Dropdown(
-                    ["base", "small"], label="Modelo", info="Modelos de Lara entrenados"
-                )
         ],
         outputs=[
-            gr.Text(label="Salida"),
+            gr.Text(label="Salida (Base)"),
+            gr.Text(label="Salida (Small)"),
+            gr.Text(label="Salida (Base 2000)"),
             gr.Number(label="Tiempo")
         ])
-demo.launch()
+demo.launch()