Create app.py

app.py

@@ -0,0 +1,47 @@
+!pip install -q git+https://github.com/openai/whisper.git
+!pip install -q gradio
+!pip install -q deepl
+!pip install -q requests
+
+import whisper
+model = whisper.load_model("base")
+
+import deepl
+deepl_auth_key = os.environ["ElevenLabs_API"]
+
+def translate(text, target_lang):
+  translator = deepl.Translator(deepl_auth_key)
+  translated_text = translator.translate_text(text, target_lang=target_lang)
+  return translated_text
+
+def transcribe(audio):
+
+    # load audio and pad/trim it to fit 30 seconds
+    audio = whisper.load_audio(audio)
+    audio = whisper.pad_or_trim(audio)
+
+    # make log-Mel spectrogram and move to the same device as the model
+    mel = whisper.log_mel_spectrogram(audio).to(model.device)
+
+    # detect the spoken language
+    _, probs = model.detect_language(mel)
+    print(f"Detected language: {max(probs, key=probs.get)}")
+    detect_lang = max(probs, key=probs.get)
+
+    # decode the audio
+    options = whisper.DecodingOptions()
+    result = whisper.decode(model, mel, options)
+
+
+    translated_text = translate(result.text, "JA")
+    return translated_text
+
+import gradio as gr
+
+title = 'Video Translator'
+
+inputs = gr.Video()
+outputs = gr.Text()
+interface = gr.Interface(title=title, fn=transcribe, inputs=inputs, outputs=outputs)
+interface.launch(debug=True)
+