Update app.py

app.py

@@ -1,104 +1,26 @@
-import os
-os.system("pip install git+https://github.com/openai/whisper.git")
 import gradio as gr
 import whisper
-
-model = whisper.load_model("small")
-
-def transcription(audio):
-    result = model.transcribe(audio)
-    return result['text']
-
-
-title = " "
-
-description=" "
-
-css = """
-        footer {visibility: hidden}
-        .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%;
-        }
-"""
-
-block = gr.Blocks(css=css)
-
-
-
-with block:
-    gr.HTML(
-        """
-            <div style="text-align: center; max-width: 650px; margin: 0 auto;">
-
-            </div>
-        """
-    )
-    with gr.Group():
-        with gr.Box():
-            with gr.Row().style(mobile_collapse=False, equal_height=True):
-                audio = gr.Audio()   
-                btn = gr.Button("Transcribe")
-        text = gr.Textbox(show_label=False)
-        
-        btn.click(transcription, inputs=[audio], outputs=[text])
- 
-
-
-block.launch()
+from langcodes import *
+
+def speech_to_text(tmp_filename, uploaded, model_size):
+    model = whisper.load_model(model_size)
+    source = uploaded if uploaded is not None else tmp_filename
+    result = model.transcribe(source)
+    return f'Detected language: {Language.make(language=result["language"]).display_name()}\n\n You said: {result["text"]}'
+
+
+gr.Interface(
+   
+    title="Whisper by OpenAI",
+    thumbnail="https://cdn.openai.com/whisper/asr-summary-of-model-architecture-desktop.svg",
+    css="""
+    .gr-prose p{text-align: center;}
+    .gr-button {background: black;color: white}
+    """,
+    description="Whisper is an automatic speech recognition (ASR) system trained on 680,000 hours of multilingual and multitask supervised data collected from the web.",
+    fn=speech_to_text,
+    inputs=[
+        gr.Audio(label="Record your voice on your mic",source="microphone", type="filepath"),
+        gr.Audio(source="upload", type="filepath", label="Upload Audio"), 
+        gr.Dropdown(label="Select model size",value="base",choices=["tiny", "base", "small", "medium", "large"])],
+    outputs="text").launch()