基于Wav2Vec 2.0的波斯语（Farsi - fa）语音情感识别

使用方法

环境要求

# 所需安装包
!pip install git+https://github.com/huggingface/datasets.git
!pip install git+https://github.com/huggingface/transformers.git
!pip install torchaudio
!pip install librosa

预测示例

import torch
import torch.nn as nn
import torch.nn.functional as F
import torchaudio
from transformers import AutoConfig, Wav2Vec2FeatureExtractor

import librosa
import IPython.display as ipd
import numpy as np
import pandas as pd

device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
model_name_or_path = "m3hrdadfi/wav2vec2-xlsr-persian-speech-emotion-recognition"
config = AutoConfig.from_pretrained(model_name_or_path)
feature_extractor = Wav2Vec2FeatureExtractor.from_pretrained(model_name_or_path)
sampling_rate = feature_extractor.sampling_rate
model = Wav2Vec2ForSpeechClassification.from_pretrained(model_name_or_path).to(device)

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

path = "/path/to/sadness.wav"
outputs = predict(path, sampling_rate)

[
{'Label': '愤怒', 'Score': '0.0%'},
{'Label': '恐惧', 'Score': '0.0%'},
{'Label': '快乐', 'Score': '0.0%'},
{'Label': '中性', 'Score': '0.0%'},
{'Label': '悲伤', 'Score': '99.9%'},
{'Label': '惊讶', 'Score': '0.0%'}
]

评估结果

下表展示了模型整体及各类别的评估指标表现。

问题反馈？

请通过此处提交Github issue。