Create app.py

app.py

@@ -0,0 +1,60 @@
+import torch
+from transformers import pipeline
+from datasets import load_dataset
+
+pipe = pipeline(
+    "automatic-speech-recognition", model="openai/whisper-base"
+)
+def translate(audio):
+    outputs = pipe(audio, max_new_tokens=256, generate_kwargs={"task": "translate"})
+    return outputs["text"]
+
+from transformers import SpeechT5Processor, SpeechT5ForTextToSpeech, SpeechT5HifiGan
+
+processor = SpeechT5Processor.from_pretrained("microsoft/speecht5_tts")
+
+model = SpeechT5ForTextToSpeech.from_pretrained("microsoft/speecht5_tts")
+vocoder = SpeechT5HifiGan.from_pretrained("microsoft/speecht5_hifigan")
+
+embeddings_dataset = load_dataset("Matthijs/cmu-arctic-xvectors", split="validation")
+speaker_embeddings = torch.tensor(embeddings_dataset[144]["gitgato/mabama-tts"]).unsqueeze(0)
+
+def synthesise(text):
+    inputs = processor(text=text, return_tensors="pt")
+    speech = model.generate_speech(
+        inputs["input_ids"], speaker_embeddings, vocoder=vocoder
+    )
+    return speech.cpu()
+
+import numpy as np
+
+target_dtype = np.int16
+max_range = np.iinfo(target_dtype).max
+
+
+def speech_to_speech_translation(audio):
+    translated_text = translate(audio)
+    synthesised_speech = synthesise(translated_text)
+    synthesised_speech = (synthesised_speech.numpy() * max_range).astype(np.int16)
+    return 16000, synthesised_speech
+
+import gradio as gr
+
+demo = gr.Blocks()
+
+mic_translate = gr.Interface(
+    fn=speech_to_speech_translation,
+    inputs=gr.Audio(sources=["microphone"], type="filepath"),
+    outputs=gr.Audio(label="Generated Speech", type="numpy"),
+)
+
+file_translate = gr.Interface(
+    fn=speech_to_speech_translation,
+    inputs=gr.Audio(sources=["upload"], type="filepath"),
+    outputs=gr.Audio(label="Generated Speech", type="numpy"),
+)
+
+with demo:
+    gr.TabbedInterface([mic_translate, file_translate], ["Microphone", "Audio File"])
+
+demo.launch(debug=True)