init!

app.py

@@ -0,0 +1,56 @@
+import gradio as gr 
+import time
+import whisper
+import cohere
+#from dotenv import load_dotenv
+
+#load_dotenv()
+co = cohere.Client('0brA5yZUeNlQM98z5h4XQAiYYpCGNMbGPjk5ghE6')
+
+model = whisper.load_model("base")
+
+def transcribe(audio):
+    
+    #time.sleep(3)
+    # load audio and pad/trim it to fit 30 seconds
+    audio = whisper.load_audio(audio)
+    audio = whisper.pad_or_trim(audio)
+
+    # make log-Mel spectrogram and move to the same device as the model
+    mel = whisper.log_mel_spectrogram(audio).to(model.device)
+
+    # detect the spoken language
+    _, probs = model.detect_language(mel)
+    print(f"Detected language: {max(probs, key=probs.get)}")
+
+    # decode the audio
+    options = whisper.DecodingOptions()
+    result = whisper.decode(model, mel, options)
+
+    #cohere
+    response = co.generate(
+    model='xlarge',
+    prompt=f'This program will generate an introductory paragraph to a blog post given a blog title, audience, and tone of voice.\n--\nBlog Title: Best Activities in Toronto\nAudience: Millennials\nTone of Voice: Lighthearted\nFirst Paragraph: Looking for fun things to do in Toronto? When it comes to exploring Canada\'s largest city, there\'s an ever-evolving set of activities to choose from. Whether you\'re looking to visit a local museum or sample the city\'s varied cuisine, there is plenty to fill any itinerary. In this blog post, I\'ll share some of my favorite recommendations\n--\nBlog Title: Mastering Dynamic Programming\nAudience: Developers\nTone: Informative\nFirst Paragraph: In this piece, we\'ll help you understand the fundamentals of dynamic programming, and when to apply this optimization technique. We\'ll break down bottom-up and top-down approaches to solve dynamic programming problems.\n--\nBlog Title: {result.text}\nAudience: Athletes\nTone: Enthusiastic\nFirst Paragraph:',
+    max_tokens=100,
+    temperature=0.8,
+    k=0,
+    p=1,
+    frequency_penalty=0,
+    presence_penalty=0,
+    stop_sequences=["--"],
+    return_likelihoods='NONE')
+    #result.text
+    reptxt = response.generations[0].text.strip("--")
+    
+    return  reptxt
+
+
+
+gr.Interface(
+    title = 'OpenAI Whisper ASR Gradio Web UI', 
+    fn=transcribe, 
+    inputs=[
+        gr.inputs.Audio(source="microphone", type="filepath")
+    ],
+    outputs=["text"],
+    live=True).launch(share=True)