Spaces:
Runtime error
Runtime error
File size: 4,836 Bytes
eb47f12 cd87708 3ea90d5 eb47f12 cd87708 786bfcc eb47f12 cd87708 eb47f12 0b0500e 42b0cc1 eb47f12 62848ce cd87708 0e5f7d6 cd87708 17693a4 cd87708 eb47f12 cd87708 0e5f7d6 eb47f12 0e5f7d6 62848ce 0e5f7d6 974e3f8 0e5f7d6 eb47f12 0e5f7d6 eb47f12 cd87708 eb47f12 81240b7 eb47f12 d5721f7 eb47f12 81240b7 eb47f12 3ea90d5 eb47f12 81240b7 eb47f12 0b0500e eb47f12 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 |
import os
import openai
import whisper
import gradio as gr
openai.api_key = os.environ.get('SessionToken')
whisper_model = whisper.load_model("small")
conversation = ""
user_name = "MH"
bot_name = "bbDemo"
def chat_hf(audio):
conversation = ""
try:
whisper_text = translate(audio)
user_input = whisper_text
# Conversation route
prompt = user_name + ": " + user_input + "\n" + bot_name+ ": "
conversation += prompt # allows for context
# fetch the response from open AI api
response = openai.Completion.create(engine='text-davinci-003', prompt=conversation, max_tokens=50)
response_str = response["choices"][0]["text"].replace("\n", "")
response_str = response_str.split(user_name + ": ", 1)[0].split(bot_name + ": ", 1)[0]
conversation += response_str + "\n"
gpt_response = response_str
except:
# Conversation route
whisper_text = translate(audio)
user_input = whisper_text
prompt = user_name + ": " + user_input + "\n" + bot_name+ ": "
conversation += prompt # allows for context
# fetch the response from open AI api
response = openai.Completion.create(engine='text-davinci-003', prompt=conversation, max_tokens=1024)
response_str = response["choices"][0]["text"].replace("\n", "")
response_str = response_str.split(user_name + ": ", 1)[0].split(bot_name + ": ", 1)[0]
conversation += response_str + "\n"
gpt_response = response_str
print("Error")
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)
transcription = whisper.decode(whisper_model, mel, transcript_options)
print("language spoken: " + transcription.language)
print("transcript: " + transcription.text)
print("———————————————————————————————————————————")
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 />
</p>
<p style="font-size: 94%">
<span style="display: flex;align-items: center;justify-content: center;height: 30px;">
</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://englishphonetics.net/" target="_blank">Eriberto Oliveira</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;
}
'''
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 !")
with gr.Column():
audio_translation = gr.Textbox(type="text",label="Whisper transcription")
gpt_response = gr.Textbox(type="text",label="chatGPT response")
gr.HTML(article)
send_btn.click(chat_hf, inputs=[record_input], outputs=[audio_translation, gpt_response])
demo.queue(max_size=32, concurrency_count=20).launch(debug=True) |