File size: 3,565 Bytes
4c391c9 |
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 |
import gradio as gr
import whisper
from transformers import pipeline
import librosa
import soundfile as sf
import tempfile
model = whisper.load_model("base")
sentiment_analysis = pipeline(
"sentiment-analysis",
framework="pt",
model="SamLowe/roberta-base-go_emotions"
)
def analyze_sentiment(text):
results = sentiment_analysis(text)
sentiment_results = {
result['label']: result['score'] for result in results
}
return sentiment_results
def get_sentiment_emoji(sentiment):
# Define the mapping of sentiments to emojis
emoji_mapping = {
"disappointment": "😞",
"sadness": "😢",
"annoyance": "😠",
"neutral": "😐",
"disapproval": "👎",
"realization": "😮",
"nervousness": "😬",
"approval": "👍",
"joy": "😄",
"anger": "😡",
"embarrassment": "😳",
"caring": "🤗",
"remorse": "😔",
"disgust": "🤢",
"grief": "😥",
"confusion": "😕",
"relief": "😌",
"desire": "😍",
"admiration": "😌",
"optimism": "😊",
"fear": "😨",
"love": "❤️",
"excitement": "🎉",
"curiosity": "🤔",
"amusement": "😄",
"surprise": "😲",
"gratitude": "🙏",
"pride": "🦁"
}
return emoji_mapping.get(sentiment, "")
def display_sentiment_results(sentiment_results, option):
sentiment_text = ""
for sentiment, score in sentiment_results.items():
emoji = get_sentiment_emoji(sentiment)
score_percentage = score * 100 # Corrected indentation
if option == "Sentiment Only":
sentiment_text += f"{sentiment} {emoji}\n"
elif option == "Sentiment + Score":
sentiment_text += f"{sentiment} {emoji}: {score_percentage:.2f}%\n"
return sentiment_text
def load_and_resample_audio(file_path, target_sample_rate=16000):
audio, _ = librosa.load(file_path, sr=target_sample_rate)
temp_file_path = '/tmp/resampled_audio.wav'
sf.write(temp_file_path, audio, target_sample_rate)
return temp_file_path
def inference(audio_file_path, sentiment_option):
resampled_audio_path = load_and_resample_audio(audio_file_path)
audio = whisper.load_audio(resampled_audio_path)
audio = whisper.pad_or_trim(audio)
mel = whisper.log_mel_spectrogram(audio).to(model.device)
_, probs = model.detect_language(mel)
lang = max(probs, key=probs.get)
options = whisper.DecodingOptions(fp16=False)
result = whisper.decode(model, mel, options)
sentiment_results = analyze_sentiment(result.text)
sentiment_output = display_sentiment_results(sentiment_results, sentiment_option)
return lang.upper(), result.text, sentiment_output
title = "🎤 Gradio UI"
description = "we have deployed our model on Gradio"
block = gr.Blocks()
with block:
gr.Markdown("# Mood Reader 🕵️♂️")
gr.Markdown("Your Words Whisper 🤫, But Emotions Shout 📢 – Discover What's Truly Behind Every Sentence with Mood Reader 🕵️♂️💬")
with gr.Column():
audio = gr.Audio(label="Input Audio", type="filepath")
sentiment_option = gr.Radio(choices=["Sentiment Only", "Sentiment + Score"], label="Select an option")
transcribe_btn = gr.Button("Transcribe")
lang_str = gr.Textbox(label="Language")
text = gr.Textbox(label="Transcription")
sentiment_output = gr.Textbox(label="Sentiment Analysis Results")
transcribe_btn.click(
inference,
inputs=[audio, sentiment_option],
outputs=[lang_str, text, sentiment_output]
)
block.launch()
|