| import os |
| os.system("pip install git+https://github.com/openai/whisper.git") |
| import gradio as gr |
| import whisper |
| import openai |
|
|
| from share_btn import community_icon_html, loading_icon_html, share_js |
|
|
| model = whisper.load_model("base") |
|
|
| mes1 = [ |
| {"role": "system", "content": "You are a TOEFL examiner who will ask me questions in a TOEFL test."} |
| ] |
|
|
| mes2 = [ |
| {"role": "system", "content": "You are a mental health therapist. Your name is Tina."} |
| ] |
|
|
| mes3 = [ |
| {"role": "system", "content": "You are my personal assistant. Your name is Alice."} |
| ] |
|
|
| res = [] |
|
|
| def inference(apikey, audio, choice1): |
|
|
| |
|
|
| openai.api_key = apikey |
| |
| |
| |
| audio = whisper.load_audio(audio) |
| audio = whisper.pad_or_trim(audio) |
|
|
| |
| mel = whisper.log_mel_spectrogram(audio).to(model.device) |
|
|
| |
| _, probs = model.detect_language(mel) |
| print(f"Detected language: {max(probs, key=probs.get)}") |
|
|
| |
| options = whisper.DecodingOptions() |
| result = whisper.decode(model, mel, options) |
| res.append(result.text) |
|
|
| if choice1 == "TOEFL": |
| messages = mes1 |
| elif choice1 == "Therapist": |
| messages = mes2 |
| elif choice1 == "Alice": |
| messages = mes3 |
|
|
| |
| n = len(res) |
| content = res[n-1] |
| 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 [result.text, chat_response, gr.update(visible=True), gr.update(visible=True), gr.update(visible=True)] |
|
|
|
|
| css = """ |
| .gradio-container { |
| font-family: 'IBM Plex Sans', sans-serif; |
| } |
| .gr-button { |
| color: white; |
| border-color: black; |
| background: black; |
| } |
| input[type='range'] { |
| accent-color: black; |
| } |
| .dark input[type='range'] { |
| accent-color: #dfdfdf; |
| } |
| .container { |
| max-width: 730px; |
| margin: auto; |
| padding-top: 1.5rem; |
| } |
| |
| .details:hover { |
| text-decoration: underline; |
| } |
| .gr-button { |
| white-space: nowrap; |
| } |
| .gr-button:focus { |
| border-color: rgb(147 197 253 / var(--tw-border-opacity)); |
| outline: none; |
| box-shadow: var(--tw-ring-offset-shadow), var(--tw-ring-shadow), var(--tw-shadow, 0 0 #0000); |
| --tw-border-opacity: 1; |
| --tw-ring-offset-shadow: var(--tw-ring-inset) 0 0 0 var(--tw-ring-offset-width) var(--tw-ring-offset-color); |
| --tw-ring-shadow: var(--tw-ring-inset) 0 0 0 calc(3px var(--tw-ring-offset-width)) var(--tw-ring-color); |
| --tw-ring-color: rgb(191 219 254 / var(--tw-ring-opacity)); |
| --tw-ring-opacity: .5; |
| } |
| .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; |
| } |
| .prompt h4{ |
| margin: 1.25em 0 .25em 0; |
| font-weight: bold; |
| font-size: 115%; |
| } |
| .animate-spin { |
| animation: spin 1s linear infinite; |
| } |
| @keyframes spin { |
| from { |
| transform: rotate(0deg); |
| } |
| to { |
| transform: rotate(360deg); |
| } |
| } |
| #share-btn-container { |
| display: flex; margin-top: 1.5rem !important; padding-left: 0.5rem !important; padding-right: 0.5rem !important; background-color: #000000; justify-content: center; align-items: center; border-radius: 9999px !important; width: 13rem; |
| } |
| #share-btn { |
| all: initial; color: #ffffff;font-weight: 600; cursor:pointer; font-family: 'IBM Plex Sans', sans-serif; margin-left: 0.5rem !important; padding-top: 0.25rem !important; padding-bottom: 0.25rem !important; |
| } |
| #share-btn * { |
| all: unset; |
| } |
| """ |
|
|
| block = gr.Blocks(css=css) |
|
|
|
|
|
|
| with block: |
| gr.HTML( |
| """ |
| <div style="text-align: center; max-width: 650px; margin: 0 auto;"> |
| <div |
| style=" |
| display: inline-flex; |
| align-items: center; |
| gap: 0.8rem; |
| font-size: 1.75rem; |
| " |
| > |
| <svg |
| width="0.65em" |
| height="0.65em" |
| viewBox="0 0 115 115" |
| fill="none" |
| xmlns="http://www.w3.org/2000/svg" |
| > |
| <rect width="23" height="23" fill="white"></rect> |
| <rect y="69" width="23" height="23" fill="white"></rect> |
| <rect x="23" width="23" height="23" fill="#AEAEAE"></rect> |
| <rect x="23" y="69" width="23" height="23" fill="#AEAEAE"></rect> |
| <rect x="46" width="23" height="23" fill="white"></rect> |
| <rect x="46" y="69" width="23" height="23" fill="white"></rect> |
| <rect x="69" width="23" height="23" fill="black"></rect> |
| <rect x="69" y="69" width="23" height="23" fill="black"></rect> |
| <rect x="92" width="23" height="23" fill="#D9D9D9"></rect> |
| <rect x="92" y="69" width="23" height="23" fill="#AEAEAE"></rect> |
| <rect x="115" y="46" width="23" height="23" fill="white"></rect> |
| <rect x="115" y="115" width="23" height="23" fill="white"></rect> |
| <rect x="115" y="69" width="23" height="23" fill="#D9D9D9"></rect> |
| <rect x="92" y="46" width="23" height="23" fill="#AEAEAE"></rect> |
| <rect x="92" y="115" width="23" height="23" fill="#AEAEAE"></rect> |
| <rect x="92" y="69" width="23" height="23" fill="white"></rect> |
| <rect x="69" y="46" width="23" height="23" fill="white"></rect> |
| <rect x="69" y="115" width="23" height="23" fill="white"></rect> |
| <rect x="69" y="69" width="23" height="23" fill="#D9D9D9"></rect> |
| <rect x="46" y="46" width="23" height="23" fill="black"></rect> |
| <rect x="46" y="115" width="23" height="23" fill="black"></rect> |
| <rect x="46" y="69" width="23" height="23" fill="black"></rect> |
| <rect x="23" y="46" width="23" height="23" fill="#D9D9D9"></rect> |
| <rect x="23" y="115" width="23" height="23" fill="#AEAEAE"></rect> |
| <rect x="23" y="69" width="23" height="23" fill="black"></rect> |
| </svg> |
| <h1 style="font-weight: 900; margin-bottom: 7px;"> |
| TalktoAI๏ผ้ๆถ้ๅฐ๏ผ่ฐๅคฉ่ฏดๅฐ๏ผ |
| </h1> |
| </div> |
| <p style="margin-bottom: 10px; font-size: 94%"> |
| ่ฎฉๆไบบๆๅ
ณๆ็AI้ ็ฆๆฏไธไธชไบบ๏ผAIๅๅ๏ผๆๆ็็จ๏ผ |
| </p> |
| </div> |
| """ |
| ) |
|
|
| with gr.Group(): |
| with gr.Box(): |
| with gr.Row().style(mobile_collapse=False, equal_height=True): |
| apikey = gr.Textbox(lines=3, label = "่ฏทๅกซๅๆจ็OpenAI_API_key") |
| audio = gr.Audio( |
| label="Input Audio", |
| show_label=False, |
| source="microphone", |
| type="filepath" |
| ) |
| choice1 = gr.Radio(["TOEFL", "Therapist", "Alice"], label="TOEFL Examiner, Therapist Tina, or Assistant Alice?") |
|
|
| btn = gr.Button("ๆไบค") |
|
|
| text = gr.Textbox(label="Speech to Text", elem_id="result-textarea") |
|
|
| response = gr.Textbox(label="ChatGPT Output") |
|
|
| with gr.Group(elem_id="share-btn-container"): |
| community_icon = gr.HTML(community_icon_html, visible=False) |
| loading_icon = gr.HTML(loading_icon_html, visible=False) |
| share_button = gr.Button("Share to community", elem_id="share-btn", visible=False) |
| |
|
|
|
|
| |
| btn.click(inference, inputs=[apikey, audio, choice1], outputs=[text, response, community_icon, loading_icon, share_button]) |
| share_button.click(None, [], [], _js=share_js) |
| |
| gr.HTML(''' |
| <div class="footer"> |
| <p>Model by <a href="https://github.com/openai/whisper" style="text-decoration: underline;" target="_blank">OpenAI</a> - Gradio Demo by ๐ค Hugging Face |
| </p> |
| </div> |
| ''') |
|
|
| block.launch() |
