Update app.py

app.py

@@ -1,13 +1,35 @@
-import streamlit as st
-from transformers import pipeline
+import torch
+from transformers import AutoModelForSpeechSeq2Seq, AutoProcessor, pipeline
+from datasets import load_dataset
 
-print('I am alive!')
 
-def image2text(url):
-    image_to_text_pipe = pipeline("image-to-text", model="Salesforce/blip-image-captioning-large")
-    text = image_to_text_pipe(url)[0]['generated_text']
+device = "cuda:0" if torch.cuda.is_available() else "cpu"
+torch_dtype = torch.float16 if torch.cuda.is_available() else torch.float32
 
-    print(text)
-    return text
+model_id = "openai/whisper-large-v3"
 
-image2text(Capture.PNG)
+model = AutoModelForSpeechSeq2Seq.from_pretrained(
+    model_id, torch_dtype=torch_dtype, low_cpu_mem_usage=True, use_safetensors=True
+)
+model.to(device)
+
+processor = AutoProcessor.from_pretrained(model_id)
+
+pipe = pipeline(
+    "automatic-speech-recognition",
+    model=model,
+    tokenizer=processor.tokenizer,
+    feature_extractor=processor.feature_extractor,
+    max_new_tokens=128,
+    chunk_length_s=30,
+    batch_size=16,
+    return_timestamps=True,
+    torch_dtype=torch_dtype,
+    device=device,
+)
+
+dataset = load_dataset("distil-whisper/librispeech_long", "clean", split="validation")
+sample = dataset[0]["audio"]
+
+result = pipe(sample)
+print(result["text"])