Create app.py

app.py

@@ -0,0 +1,44 @@
+import torch
+from transformers import AutoModelForSpeechSeq2Seq, AutoProcessor, pipeline
+from datasets import load_dataset
+import gradio as gr
+import librosa
+
+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
+)
+model.to(device)
+
+processor = AutoProcessor.from_pretrained(model_id)
+
+pipe = pipeline(
+    "automatic-speech-recognition",
+    model=model,
+    tokenizer=processor.tokenizer,
+    feature_extractor=processor.feature_extractor,
+    torch_dtype=torch_dtype,
+    device=device,
+)
+
+# dataset = load_dataset("distil-whisper/librispeech_long", "clean", split="validation")
+# sample = dataset[0]["audio"]
+def transcribe(audio):
+  print(audio)
+  if audio is None:
+    return "Please record or upload audio"
+  speech , sr = librosa.load(audio)
+  result = pipe(speech,return_timestamps=True)
+  return result["text"]
+
+
+gr.Interface( fn = transcribe,
+             inputs= gr.Audio(),
+              outputs ="text",
+              title="Whisper transcription App",
+              description ="Record or upload audio and get transcription").launch(debug=True)
+