app.py

import torch
import torchaudio
from transformers import Wav2Vec2FeatureExtractor,AutoConfig,pipeline

config = AutoConfig.from_pretrained("SeyedAli/Persian-Speech-Emotion-HuBert-V1")
model = Wav2Vec2FeatureExtractor.from_pretrained("SeyedAli/Persian-Speech-Emotion-HuBert-V1")

def speech_file_to_array_fn(path, sampling_rate):
    speech_array, _sampling_rate = torchaudio.load(path)
    resampler = torchaudio.transforms.Resample(_sampling_rate)
    speech = resampler(speech_array).squeeze().numpy()
    return speech

def predict(path, sampling_rate):
    speech = speech_file_to_array_fn(path, sampling_rate)
    inputs = feature_extractor(speech, sampling_rate=sampling_rate, return_tensors="pt", padding=True)
    inputs = {key: inputs[key].to(device) for key in inputs}

    with torch.no_grad():
        logits = model(**inputs).logits

    scores = F.softmax(logits, dim=1).detach().cpu().numpy()[0]
    outputs = [{"Label": config.id2label[i], "Score": f"{round(score * 100, 3):.1f}%"} for i, score in enumerate(scores)]
    return outputs

def SER(Audio):
    return predict(Audio,model.sampling_rate)

iface = gr.Interface(fn=SER, inputs="audio", outputs="text")
iface.launch(share=False)