Spaces:
Sleeping
Sleeping
| import gradio as gr | |
| import numpy as np | |
| import torch | |
| from transformers import pipeline | |
| import librosa | |
| import soundfile as sf | |
| class EmotionRecognizer: | |
| def __init__(self): | |
| self.classifier = pipeline( | |
| "audio-classification", | |
| model="ehcalabres/wav2vec2-lg-xlsr-en-speech-emotion-recognition", | |
| device=0 if torch.cuda.is_available() else -1 | |
| ) | |
| self.target_sr = 16000 # Target sample rate for the model | |
| self.max_duration = 10 # Max audio duration in seconds | |
| def process_audio(self, audio_path): | |
| try: | |
| # Load audio file using soundfile (works better in Hugging Face Spaces) | |
| audio, orig_sr = sf.read(audio_path) | |
| # Convert stereo to mono if needed | |
| if len(audio.shape) > 1: | |
| audio = np.mean(audio, axis=1) | |
| # Resample if necessary | |
| if orig_sr != self.target_sr: | |
| audio = librosa.resample( | |
| y=audio.astype(np.float32), | |
| orig_sr=orig_sr, | |
| target_sr=self.target_sr | |
| ) | |
| else: | |
| audio = audio.astype(np.float32) | |
| # Normalize audio | |
| audio = librosa.util.normalize(audio) | |
| # Trim/pad audio to max duration | |
| max_samples = self.max_duration * self.target_sr | |
| if len(audio) > max_samples: | |
| audio = audio[:max_samples] | |
| else: | |
| audio = np.pad(audio, (0, max(0, max_samples - len(audio)))) | |
| # Run classification | |
| results = self.classifier( | |
| {"array": audio, "sampling_rate": self.target_sr} | |
| ) | |
| # Format output | |
| labels = [res["label"] for res in results] | |
| scores = [res["score"] * 100 for res in results] | |
| text_output = "\n".join([ | |
| f"{label}: {score:.2f}%" | |
| for label, score in zip(labels, scores) | |
| ]) | |
| plot_data = { | |
| "labels": labels, | |
| "values": scores | |
| } | |
| return text_output, plot_data | |
| except Exception as e: | |
| error_msg = f"Error processing audio: {str(e)}" | |
| print(error_msg) | |
| return error_msg, None | |
| def create_interface(): | |
| recognizer = EmotionRecognizer() | |
| with gr.Blocks(title="Audio Emotion Recognition") as interface: | |
| gr.Markdown("# 🎙️ Audio Emotion Recognition") | |
| gr.Markdown("Record or upload audio (English speech, 3-10 seconds)") | |
| with gr.Row(): | |
| with gr.Column(): | |
| audio_input = gr.Audio( | |
| sources=["microphone", "upload"], | |
| type="filepath", | |
| label="Input Audio", | |
| waveform_options={"waveform_progress_color": "#FF0066"} | |
| ) | |
| submit_btn = gr.Button("Analyze", variant="primary") | |
| with gr.Column(): | |
| text_output = gr.Textbox( | |
| label="Emotion Analysis Results", | |
| interactive=False | |
| ) | |
| plot_output = gr.BarPlot( | |
| label="Confidence Scores", | |
| x="labels", | |
| y="values", | |
| color="labels", | |
| height=300 | |
| ) | |
| submit_btn.click( | |
| fn=recognizer.process_audio, | |
| inputs=audio_input, | |
| outputs=[text_output, plot_output] | |
| ) | |
| gr.Examples( | |
| examples=[ | |
| "https://huggingface.co/spaces/echalabres/emotion-recognition/raw/main/example_angry.wav", | |
| "https://huggingface.co/spaces/echalabres/emotion-recognition/raw/main/example_happy.wav" | |
| ], | |
| inputs=audio_input, | |
| outputs=[text_output, plot_output], | |
| fn=recognizer.process_audio, | |
| cache_examples=True | |
| ) | |
| return interface | |
| if __name__ == "__main__": | |
| demo = create_interface() | |
| demo.launch() |