Spaces:
Runtime error
Runtime error
File size: 5,527 Bytes
0899e82 e0c2b71 f488509 e0c2b71 f488509 c6c6f6f ddab9eb 7dd7859 c6c6f6f 8b338c8 417aaff 7dd7859 6452498 dbe0d2a ddab9eb dd9eb54 232e486 77a2b12 232e486 dbe0d2a 3ccd8bb c6c6f6f e3ec47c a846d22 8b338c8 a846d22 717ce50 cff6b7f 717ce50 dbe0d2a |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 |
import gradio as gr
import torch
import whisper
from transformers import pipeline
### ————————————————————————————————————————
title="Whisper to Emotion"
### ————————————————————————————————————————
whisper_model = whisper.load_model("small")
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
emotion_classifier = pipeline("text-classification",model='bhadresh-savani/distilbert-base-uncased-emotion')
def translate_and_classify(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("Translated: " + translation.text)
emotion = emotion_classifier(translation.text)
detected_emotion = emotion[0]["label"]
return transcription.text, detected_emotion
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;
}
#gallery {
min-height: 22rem;
margin-bottom: 15px;
margin-left: auto;
margin-right: auto;
border-bottom-right-radius: .5rem !important;
border-bottom-left-radius: .5rem !important;
}
#gallery>div>.h-full {
min-height: 20rem;
}
.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;
}
#advanced-btn {
font-size: .7rem !important;
line-height: 19px;
margin-top: 12px;
margin-bottom: 12px;
padding: 2px 8px;
border-radius: 14px !important;
}
#advanced-options {
display: none;
margin-bottom: 20px;
}
.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:
gr.Markdown("""
## Emotion Detection From Speech with Whisper
""")
gr.HTML('''
<p style="margin-bottom: 10px; font-size: 94%">
Whisper is a general-purpose speech recognition model released by OpenAI that can perform multilingual speech recognition as well as speech translation and language identification. This allows for detecting emotion directly from speech in multiple languages
</p>
''')
with gr.Row():
#gr.Markdown(""" ### Record audio """)
audio_input = gr.Audio(label = 'Record Audio Input',source="microphone",type="filepath")
with gr.Row():
transcribe_audio = gr.Button('Transcribe')
with gr.Row():
transcript_output = gr.Textbox(label="Transcription in the language you spoke", lines = 3)
emotion_output = gr.Textbox(label = "Detected Emotion")
transcribe_audio.click(translate_and_classify, inputs = audio_input, outputs = [transcript_output,emotion_output])
gr.HTML('''
<div class="footer">
<p>Whisper Model by <a href="https://github.com/openai/whisper" style="text-decoration: underline;" target="_blank">OpenAI</a> -
<a href="https://huggingface.co/bhadresh-savani/distilbert-base-uncased-emotion" style="text-decoration: underline;" target="_blank">Emotion Detection Model</a>
</p>
</div>
''')
demo.launch() |