Update app.py

app.py

@@ -2,22 +2,34 @@ import gradio as gr
 from transformers import pipeline,WhisperProcessor, WhisperForConditionalGeneration
 import torch
 import librosa
+import datasets
+from transformers.pipelines.pt_utils import KeyDataset
+from tqdm.auto import tqdm
 
-checkpoint = "openai/whisper-base"
+transcriber = pipeline(model="openai/whisper-large-v2",device_map="auto")
 # checkpoint = "/innev/open-ai/huggingface/openai/whisper-base"
 image_to_text_model = pipeline("image-classification")
 text_to_audio_model = pipeline("text-to-speech")
+pipe_audio = pipeline("automatic-speech-recognition", model="facebook/wav2vec2-base-960h", device=0)
+dataset = datasets.load_dataset("superb", name="asr", split="test")
 
+for out in tqdm(pipe(KeyDataset(dataset, "file"))):
+    print(out)
+    # {"text": "NUMBER TEN FRESH NELLY IS WAITING ON YOU GOOD NIGHT HUSBAND"}
+    # {"text": ....}
+    # ....
 def image_to_text(input_image):
     # Convertir la imagen a texto
     text_output = image_to_text_model(input_image)[0]['label']
+    print(text_output)
+    #texts = transcriber(text_output)
     return text_output
 
-with gr.Blocks() as demo:
-    gr.Markdown("Start typing below and then click **Run** to see the output.")
-    with gr.Row():
-        inp = gr.Image()
-        out = gr.Textbox(placeholder=image_to_text(inp))
-    gr.Interface(fn=image_to_text, inputs=inp, outputs=out,interpretation="default")
+#with gr.Blocks() as demo:
+#    gr.Markdown("Start typing below and then click **Run** to see the output.")
+#    with gr.Row():
+#        inp = gr.Image()
+#        out = gr.Textbox(placeholder=image_to_text(inp))
+#    gr.Interface(fn=image_to_text, inputs=inp, outputs=out,interpretation="default")
 
-demo.launch()
+#demo.launch()