app

app.py

@@ -0,0 +1,50 @@
+#Imports
+import whisper
+import gradio as gr 
+import warnings
+from gtts import gTTS
+
+model = whisper.load_model("base")
+
+
+def transcribe(audio):
+    language = 'en'
+
+    audio = whisper.load_audio(audio)
+    audio = whisper.pad_or_trim(audio)
+
+    mel = whisper.log_mel_spectrogram(audio).to(model.device)
+
+    _, probs = model.detect_language(mel)
+    print(f"Detected language: {max(probs, key=probs.get)}")
+
+    options = whisper.DecodingOptions(fp16 = False)
+    result = whisper.decode(model, mel, options)
+    result_text = result.text
+    result_tr = model.transcribe(audio ,task='translate')
+    
+    audioobj = gTTS(text = result_tr['text'], 
+                    lang = language, 
+                    slow = False)
+    
+    audioobj.save("Temp.mp3")
+
+    return [result_text, result_tr['text'], "Temp.mp3"]
+
+
+output_1 = gr.Textbox(label="Speech to Text")
+output_2 = gr.Textbox(label="English Translation Output")
+output_3 = gr.Audio("Temp.mp3", label="English Audio")
+
+gr.Interface(
+    title = 'OpenAI Whisper ASR and Translation Gradio Web UI', 
+    fn=transcribe, 
+    inputs=[
+        # gr.inputs.Audio(source="microphone", type="filepath"),
+        gr.Audio(source="upload", type="filepath")
+    ],
+
+    outputs=[
+        output_1, output_2, output_3
+    ],
+    live=True).launch(debug=True)

requirements.txt

@@ -0,0 +1,3 @@
+tensorflow
+git+https://github.com/openai/whisper.git
+gTTS