.

README.md

@@ -1,13 +1,13 @@
 ---
-title: Algmon
-emoji: 🦀
-colorFrom: red
-colorTo: pink
-sdk: streamlit
-sdk_version: 1.10.0
+title: PaddleSpeechTTS
+emoji: 🚀
+colorFrom: pink
+colorTo: blue
+sdk: gradio
+sdk_version: 2.8.10
 app_file: app.py
 pinned: false
 license: apache-2.0
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces#reference

app.py

@@ -1,40 +1,20 @@
 import os
-os.system('pip install paddlepaddle')
-os.system('pip install paddleocr')
-from paddleocr import PaddleOCR, draw_ocr
-from PIL import Image
+
 import gradio as gr
-import torch
+from paddlespeech.cli import TTSExecutor
+
+tts_executor = TTSExecutor()
+
 
-torch.hub.download_url_to_file('https://i.imgur.com/aqMBT0i.jpg', 'example.jpg')
+def speech_generate(text: str) -> os.PathLike:
+    assert isinstance(text, str) and len(text) > 0, 'Input Chinese text...'
+    wav_file = tts_executor(text=text)
+    return wav_file
 
-def inference(img, lang):
-    ocr = PaddleOCR(use_angle_cls=True, lang=lang,use_gpu=False)
-    img_path = img.name
-    result = ocr.ocr(img_path, cls=True)[0]
-    image = Image.open(img_path).convert('RGB')
-    boxes = [line[0] for line in result]
-    txts = [line[1][0] for line in result]
-    scores = [line[1][1] for line in result]
-    im_show = draw_ocr(image, boxes, txts, scores,
-                       font_path='simfang.ttf')
-    im_show = Image.fromarray(im_show)
-    im_show.save('result.jpg')
-    return 'result.jpg'
 
-title = 'Algmon OCR'
-description = 'Gradio demo for Algmon OCR. Algmon OCR demo supports Chinese, English, French, German, Korean and Japanese. To use it, simply upload your image and choose a language from the dropdown menu, or click one of the examples to load them. Read more at the links below.'
-article = "<p style='text-align: center'><a href='https://www.paddlepaddle.org.cn/hub/scene/ocr'>Awesome multilingual OCR toolkits based on PaddlePaddle （practical ultra lightweight OCR system, support 80+ languages recognition, provide data annotation and synthesis tools, support training and deployment among server, mobile, embedded and IoT devices）</a> | <a href='https://github.com/PaddlePaddle/PaddleOCR'>Github Repo</a></p>"
-examples = [['example.jpg','en']]
-css = ".output_image, .input_image {height: 40rem !important; width: 100% !important;}"
-gr.Interface(
-    inference,
-    [gr.inputs.Image(type='file', label='Input'),gr.inputs.Dropdown(choices=['ch', 'en', 'fr', 'german', 'korean', 'japan'], type="value", default='en', label='language')],
-    gr.outputs.Image(type='file', label='Output'),
-    title=title,
-    description=description,
-    article=article,
-    examples=examples,
-    css=css,
-    enable_queue=True
-    ).launch(debug=True)
+iface = gr.Interface(
+    fn=speech_generate, 
+    inputs=gr.inputs.Textbox(placeholder='请输入文字...'),
+    outputs=gr.outputs.Audio(),
+)
+iface.launch()

packages.txt

@@ -1,3 +1 @@
-ffmpeg 
-libsm6 
-libxext6
+libsndfile1

requirements.txt

@@ -1,3 +1,3 @@
-Pillow
-Gradio
-torch
+paddlepaddle
+paddleaudio
+paddlespeech

simfang.ttf

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:521c6f7546b4eb64fa4b0cd604bbd36333a20a57e388c8e2ad2ad07b9e593864
-size 10576012