Update app.py

app.py

@@ -1,56 +1,55 @@
-# WebUI by mrfakename
-# Demo also available on HF Spaces: https://huggingface.co/spaces/mrfakename/MeloTTS
 import gradio as gr
-import os, torch, io
-os.system('python -m unidic download')
-# print("Make sure you've downloaded unidic (python -m unidic download) for this WebUI to work.")
-from melo.api import TTS
-speed = 1.0
-import tempfile
-import nltk
-nltk.download('averaged_perceptron_tagger_eng')
-device = 'cuda' if torch.cuda.is_available() else 'cpu'
-models = {
-    'EN': TTS(language='EN', device=device),
-    'ES': TTS(language='ES', device=device),
-    'FR': TTS(language='FR', device=device),
-    'ZH': TTS(language='ZH', device=device),
-    'JP': TTS(language='JP', device=device),
-    'KR': TTS(language='KR', device=device),
-}
-speaker_ids = models['EN'].hps.data.spk2id
-
-default_text_dict = {
-    'EN': 'The field of text-to-speech has seen rapid development recently.',
-    'ES': 'El campo de la conversión de texto a voz ha experimentado un rápido desarrollo recientemente.',
-    'FR': 'Le domaine de la synthèse vocale a connu un développement rapide récemment',
-    'ZH': 'text-to-speech 领域近年来发展迅速',
-    'JP': 'テキスト読み上げの分野は最近急速な発展を遂げています',
-    'KR': '최근 텍스트 음성 변환 분야가 급속도로 발전하고 있습니다.',    
+import spaces
+import torch
+
+from transformers import pipeline
+
+# Pre-Initialize
+DEVICE = "auto"
+if DEVICE == "auto":
+    DEVICE = "cuda" if torch.cuda.is_available() else "cpu"
+print(f"[SYSTEM] | Using {DEVICE} type compute device.")
+
+# Variables
+DEFAULT_TASK = "transcribe"
+BATCH_SIZE = 8
+
+repo = pipeline(task="automatic-speech-recognition", model="openai/whisper-large-v3-turbo", chunk_length_s=30, device=DEVICE)
+
+css = '''
+.gradio-container{max-width: 560px !important}
+h1{text-align:center}
+footer {
+    visibility: hidden
 }
-    
-def synthesize(text, speaker, speed, language, progress=gr.Progress()):
-    bio = io.BytesIO()
-    models[language].tts_to_file(text, models[language].hps.data.spk2id[speaker], bio, speed=speed, pbar=progress.tqdm, format='wav')
-    return bio.getvalue()
-def load_speakers(language, text):
-    if text in list(default_text_dict.values()):
-        newtext = default_text_dict[language]
-    else:
-        newtext = text
-    return gr.update(value=list(models[language].hps.data.spk2id.keys())[0], choices=list(models[language].hps.data.spk2id.keys())), newtext
-with gr.Blocks() as demo:
-    gr.Markdown('# MeloTTS Demo\n\nAn unofficial demo for [MeloTTS](https://github.com/myshell-ai/MeloTTS). **Make sure to try out several speakers, for example EN-Default!**')
-    with gr.Group():
-        speaker = gr.Dropdown(speaker_ids.keys(), interactive=True, value='EN-US', label='Speaker')
-        language = gr.Radio(['EN', 'ES', 'FR', 'ZH', 'JP', 'KR'], label='Language', value='EN')
-        speed = gr.Slider(label='Speed', minimum=0.1, maximum=10.0, value=1.0, interactive=True, step=0.1)
-        text = gr.Textbox(label="Text to speak", value=default_text_dict['EN'])
-        language.input(load_speakers, inputs=[language, text], outputs=[speaker, text])
-    btn = gr.Button('Synthesize', variant='primary')
-    aud = gr.Audio(interactive=False)
-    btn.click(synthesize, inputs=[text, speaker, speed, language], outputs=[aud])
-    gr.Markdown('Demo by [mrfakename](https://twitter.com/realmrfakename).')
-
-
-demo.queue(api_open=True, default_concurrency_limit=10).launch(show_api=True)
+'''
+
+# Functions
+@spaces.GPU(duration=10)
+def transcribe(input=None, task=DEFAULT_TASK):
+    print(input)
+    if input is None: raise gr.Error("Invalid input.")
+    output = repo(input, batch_size=BATCH_SIZE, generate_kwargs={"task": task}, return_timestamps=True)["text"]
+    return output
+
+def cloud():
+    print("[CLOUD] | Space maintained.")
+
+# Initialize
+with gr.Blocks(css=css) as main:
+    with gr.Column():
+        gr.Markdown("🪄 Transcribe audio to text.")
+        
+    with gr.Column():
+        input = gr.Audio(sources="upload", type="filepath", label="Input")
+        task = gr.Radio(["transcribe", "translate"], label="Task", value=DEFAULT_TASK)
+        submit = gr.Button("▶")
+        maintain = gr.Button("☁️")
+
+    with gr.Column():
+        output = gr.Textbox(lines=1, value="", label="Output")
+            
+    submit.click(transcribe, inputs=[input, task], outputs=[output], queue=False)
+    maintain.click(cloud, inputs=[], outputs=[], queue=False)
+
+main.launch(show_api=True)