Duplicate from Kevin676/ChatGPT-with-Voice-Cloning-for-All

Co-authored-by: Kevin Wang <Kevin676@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,34 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,14 @@
+---
+title: ChatGPT With Voice Cloning For All
+emoji: 🌖
+colorFrom: purple
+colorTo: gray
+sdk: gradio
+sdk_version: 3.25.0
+app_file: app.py
+pinned: false
+license: mit
+duplicated_from: Kevin676/ChatGPT-with-Voice-Cloning-for-All
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,144 @@
+import gradio as gr
+
+from TTS.api import TTS
+
+tts1 = TTS(model_name="tts_models/multilingual/multi-dataset/your_tts", progress_bar=False, gpu=False)
+
+tts2 = TTS("tts_models/zh-CN/baker/tacotron2-DDC-GST")
+
+import os
+
+import openai
+
+import torch
+import torchaudio
+from speechbrain.pretrained import SpectralMaskEnhancement
+
+enhance_model = SpectralMaskEnhancement.from_hparams(
+source="speechbrain/metricgan-plus-voicebank",
+savedir="pretrained_models/metricgan-plus-voicebank",
+#run_opts={"device":"cuda"},
+)
+
+mes = [
+    {"role": "system", "content": "You are my personal assistant. Try to be helpful."}
+]
+
+def chatgpt(apikey, result):
+    
+    openai.api_key = apikey
+
+    messages = mes
+
+    # chatgpt
+    content = result
+    messages.append({"role": "user", "content": content})
+
+    completion = openai.ChatCompletion.create(
+      model = "gpt-3.5-turbo",
+      messages = messages
+    )
+
+    chat_response = completion.choices[0].message.content
+
+    messages.append({"role": "assistant", "content": chat_response}) 
+
+    return chat_response
+
+def english(text_en, upload, VoiceMicrophone):
+    if upload is not None:
+        tts1.tts_to_file(text_en, speaker_wav = upload, language="en", file_path="output.wav")
+
+    else:
+        tts1.tts_to_file(text_en, speaker_wav = VoiceMicrophone, language="en", file_path="output.wav")
+    
+    noisy = enhance_model.load_audio(
+    "output.wav"
+    ).unsqueeze(0)
+
+    enhanced = enhance_model.enhance_batch(noisy, lengths=torch.tensor([1.]))
+    torchaudio.save("enhanced.wav", enhanced.cpu(), 16000)
+
+    return "enhanced.wav"
+
+def chinese(text_cn, upload1, VoiceMicrophone1):
+    if upload1 is not None:
+        tts2.tts_with_vc_to_file(
+            text_cn + "。",
+            speaker_wav=upload1,
+            file_path="ouptut1.wav"
+        )
+
+    else:
+        tts2.tts_with_vc_to_file(
+            text_cn + "。",
+            speaker_wav=VoiceMicrophone1,
+            file_path="ouptut1.wav"
+        )
+
+    return "ouptut1.wav"
+
+block = gr.Blocks()
+
+with block:
+    with gr.Group():
+        gr.Markdown(
+            """ # <center>🥳💬💕 - TalktoAI，随时随地，谈天说地！</center>
+            
+            ## <center>🤖 - 让有人文关怀的AI造福每一个人！AI向善，文明璀璨！TalktoAI - Enable the future！</center>
+            
+      """
+        )
+        
+        with gr.Box():
+            with gr.Row().style(mobile_collapse=False, equal_height=True):
+              
+                inp1 = gr.Textbox(label='请输入您的Openai-API-Key', type = "password")
+                inp2 = gr.Textbox(label='说点什么吧(中英皆可)')
+
+                btn = gr.Button("开始对话吧")
+
+        texts1 = gr.Textbox(lines=3, label="ChatGPT的回答")
+              
+        btn.click(chatgpt, [inp1, inp2], [texts1])
+
+        with gr.Box():
+            with gr.Row().style(mobile_collapse=False, equal_height=True):
+                inp3 = texts1
+                inp4 = gr.Audio(source="upload", label = "请上传您喜欢的声音(wav/mp3文件)", type="filepath")
+                inp5 = gr.Audio(source="microphone", type="filepath", label = '请用麦克风上传您喜欢的声音，与文件上传二选一即可')
+
+                btn1 = gr.Button("用喜欢的声音听一听吧(中文)")
+
+        out1 = gr.Audio(label="合成的专属声音(中文)")
+
+        btn1.click(chinese, [inp3, inp4, inp5], [out1])
+
+        with gr.Box():
+            with gr.Row().style(mobile_collapse=False, equal_height=True):
+
+                btn2 = gr.Button("用喜欢的声音听一听吧(英文)")
+
+        out2 = gr.Audio(label="合成的专属声音(英文)")
+        
+        btn2.click(english, [inp3, inp4, inp5], [out2])
+
+        gr.Markdown(
+            """ ### <center>注意❗：请不要输入或生成会对个人以及组织造成侵害的内容，此程序仅供科研、学习及娱乐使用。用户输入或生成的内容与程序开发者无关，请自觉合法合规使用，违反者一切后果自负。</center>
+            
+            ### <center>Powered by [ChatGPT](https://chat.openai.com/). Please follow me on [Bilibili](https://space.bilibili.com/501495851?spm_id_from=333.1007.0.0).</center>
+            
+      """
+        )
+        
+        gr.HTML('''
+        <div class="footer">
+                    <p>🎶🖼️🎡 - It’s the intersection of technology and liberal arts that makes our hearts sing. - Steve Jobs
+                    </p>
+                    <p>注：中文声音克隆实际上是由声音转换(Voice Conversion)实现，所以输出结果可能更像是一种新的声音，效果不一定很理想，希望大家理解(之后也会不断迭代的)！为了更好的效果，使用中文声音克隆时请尽量上传女声。
+                    </p>
+        </div>
+        ''')
+
+block.launch(show_error=True)
+

requirements.txt

@@ -0,0 +1,5 @@
+openai
+TTS
+torchaudio
+speechbrain
+gradio==3.25.0