Duplicate from fffiloni/whisper-to-chatGPT

Co-authored-by: Sylvain Filoni <[email protected]>

.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: Whisper to chatGPT
+emoji: 👄🤖
+colorFrom: indigo
+colorTo: yellow
+sdk: gradio
+sdk_version: 3.12.0
+app_file: app.py
+pinned: false
+license: apache-2.0
+duplicated_from: fffiloni/whisper-to-chatGPT
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,142 @@
+from pyChatGPT import ChatGPT
+import os
+session_token = os.environ.get('SessionToken') 
+
+import whisper
+whisper_model = whisper.load_model("small")
+ 
+
+def chat_hf(audio, custom_token):
+    try:
+        whisper_text = translate(audio)
+        api = ChatGPT(session_token) 
+        resp = api.send_message(whisper_text)
+        
+        
+        api.refresh_auth()  # refresh the authorization token
+        api.reset_conversation()  # reset the conversation
+        gpt_response = resp['message']
+
+    except:
+        whisper_text = translate(audio)
+        api = ChatGPT(custom_token) 
+        resp = api.send_message(whisper_text)
+        
+        
+        api.refresh_auth()  # refresh the authorization token
+        api.reset_conversation()  # reset the conversation
+        gpt_response = resp['message']
+    
+    return whisper_text, gpt_response
+
+
+def translate(audio):
+    print("""
+    —
+    Sending audio to Whisper ...
+    —
+    """)
+    
+    audio = whisper.load_audio(audio)
+    audio = whisper.pad_or_trim(audio)
+    
+    mel = whisper.log_mel_spectrogram(audio).to(whisper_model.device)
+    
+    _, probs = whisper_model.detect_language(mel)
+    
+    transcript_options = whisper.DecodingOptions(task="transcribe", fp16 = False)
+    #translate_options = whisper.DecodingOptions(task="translate", fp16 = False)
+    
+    transcription = whisper.decode(whisper_model, mel, transcript_options)
+    #translation = whisper.decode(whisper_model, mel, translate_options)
+    
+    print("language spoken: " + transcription.language)
+    print("transcript: " + transcription.text)
+    print("———————————————————————————————————————————")  
+    #print("translated: " + translation.text)
+      
+    return transcription.text
+
+title = """
+    <div style="text-align: center; max-width: 500px; margin: 0 auto;">
+        <div
+        style="
+            display: inline-flex;
+            align-items: center;
+            gap: 0.8rem;
+            font-size: 1.75rem;
+            margin-bottom: 10px;
+        "
+        >
+        <h1 style="font-weight: 600; margin-bottom: 7px;">
+            Whisper to chatGPT
+        </h1>
+        </div>
+        <p style="margin-bottom: 10px;font-size: 94%;font-weight: 100;line-height: 1.5em;">
+        Chat with GPT with your voice in your native language !
+        <br />If it fails enter custom session key see video for reference refer 
+        <a href="https://youtu.be/TdNSj_qgdFk" target="_blank">Bhavesh Baht video</a>
+        </p>
+        <p style="font-size: 94%">
+            You can skip the queue by duplicating this space: 
+            <span style="display: flex;align-items: center;justify-content: center;height: 30px;">
+            <a href="https://huggingface.co/fffiloni/whisper-to-chatGPT?duplicate=true"><img src="https://img.shields.io/badge/-Duplicate%20Space-blue?labelColor=white&style=flat&logo=data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAABAAAAAQCAYAAAAf8/9hAAAAAXNSR0IArs4c6QAAAP5JREFUOE+lk7FqAkEURY+ltunEgFXS2sZGIbXfEPdLlnxJyDdYB62sbbUKpLbVNhyYFzbrrA74YJlh9r079973psed0cvUD4A+4HoCjsA85X0Dfn/RBLBgBDxnQPfAEJgBY+A9gALA4tcbamSzS4xq4FOQAJgCDwV2CPKV8tZAJcAjMMkUe1vX+U+SMhfAJEHasQIWmXNN3abzDwHUrgcRGmYcgKe0bxrblHEB4E/pndMazNpSZGcsZdBlYJcEL9Afo75molJyM2FxmPgmgPqlWNLGfwZGG6UiyEvLzHYDmoPkDDiNm9JR9uboiONcBXrpY1qmgs21x1QwyZcpvxt9NS09PlsPAAAAAElFTkSuQmCC&logoWidth=14" alt="Duplicate Space"></a>       
+            </span>
+        </p>
+    </div>
+"""
+
+article = """
+    <div class="footer">
+        <p><a href="https://chat.openai.com/chat" target="_blank">chatGPT</a> 
+        by <a href="https://openai.com/" style="text-decoration: underline;" target="_blank">OpenAI</a> - 
+        Gradio Demo by 🤗 <a href="https://twitter.com/fffiloni" target="_blank">Sylvain Filoni</a>
+        </p>
+    </div>
+"""
+
+css = '''
+    #col-container {max-width: 700px; margin-left: auto; margin-right: auto;}
+    a {text-decoration-line: underline; font-weight: 600;}
+    .footer {
+            margin-bottom: 45px;
+            margin-top: 35px;
+            text-align: center;
+            border-bottom: 1px solid #e5e5e5;
+        }
+        .footer>p {
+            font-size: .8rem;
+            display: inline-block;
+            padding: 0 10px;
+            transform: translateY(10px);
+            background: white;
+        }
+        .dark .footer {
+            border-color: #303030;
+        }
+        .dark .footer>p {
+            background: #0b0f19;
+        }
+'''
+ 
+import gradio as gr
+
+with gr.Blocks(css=css) as demo:
+    
+    with gr.Column(elem_id="col-container"):
+        
+        gr.HTML(title)
+        
+        with gr.Row():
+            record_input = gr.Audio(source="microphone",type="filepath", show_label=False)
+            send_btn = gr.Button("Send my message !")
+        custom_token = gr.Textbox(label='If it fails, use your own session token', placeholder="your own session token")   
+    with gr.Column():
+        audio_translation = gr.Textbox(type="text",label="Whisper translation")
+        gpt_response = gr.Textbox(type="text",label="chatGPT response")
+
+        gr.HTML(article)
+    
+    send_btn.click(chat_hf, inputs=[record_input, custom_token], outputs=[audio_translation, gpt_response])
+
+demo.queue(max_size=32, concurrency_count=20).launch(debug=True)

requirements.txt

@@ -0,0 +1,2 @@
+pyChatGPT
+git+https://github.com/openai/whisper.git