First version

app.py

@@ -28,29 +28,37 @@ default_text_dict = {
     '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.',    
 }
-    
+def extract_text(file):
+    from pypdf import PdfReader
+    reader = PdfReader(file)
+    number_of_pages = len(reader.pages)
+    text = ''.join(page.extract_text() for page in reader.pages[:10])
+    return text
+
 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
+
+def load_speakers(language):
+    return gr.update(value=list(models[language].hps.data.spk2id.keys())[0], choices=list(models[language].hps.data.spk2id.keys()))
+
+
 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!**')
+    gr.Markdown('# PDF reader\n\nA real pdf reader based on [MeloTTS](https://github.com/myshell-ai/MeloTTS).')
     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')
+        speaker = gr.Dropdown(speaker_ids.keys(), interactive=True, value='FR', label='Speaker')
+        language = gr.Radio(['EN', 'ES', 'FR', 'ZH', 'JP', 'KR'], label='Language', value='FR')
         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')
+        file = gr.File(label="Document à lire")
+        language.input(load_speakers, inputs=[language], outputs=[speaker])
+    btn_extract = gr.Button('Extraire le texte', variant='primary')
+    text = gr.Textbox(label="Texte extrait")
+    btn = gr.Button('Réciter le texte !', variant='primary')
     aud = gr.Audio(interactive=False)
+    btn_extract.click(extract_text, inputs=[file], outputs=[text])
     btn.click(synthesize, inputs=[text, speaker, speed, language], outputs=[aud])
-    gr.Markdown('Demo by [mrfakename](https://twitter.com/realmrfakename).')
+    gr.Markdown('Demo by [m-ric](https://x.com/AymericRoucher).')
 
 
 demo.queue(api_open=True, default_concurrency_limit=10).launch(show_api=True)

requirements.txt

@@ -28,4 +28,5 @@ langid==1.1.6
 tqdm
 tensorboard==2.16.2
 loguru==0.7.2
-txtsplit
+txtsplit
+pypdf