11

app.py

@@ -3,9 +3,10 @@ import os
 import soundfile as sf
 from pydub import AudioSegment
 import numpy as np
+from transformers import Wav2Vec2Processor
+import torch
 
 def record_audio(audio):
-    # 获取音频文件路径
     audio_file = audio
     
     # 读取音频文件
@@ -27,20 +28,46 @@ def record_audio(audio):
     filename = "voice.wav"
     sf.write(filename, audio_data, sample_rate)
     
-    return "录音成功！已保存为 " + filename, audio
+    return filename  # 返回保存的文件路径
+
+def voice_sentiment(voice):
+    MODEL_ID = "jonatasgrosman/wav2vec2-large-xlsr-53-chinese-zh-cn"
+    processor = Wav2Vec2Processor.from_pretrained(MODEL_ID)
+
+    model_path = 'sentiment_rnn_model.pth'  # 已训练好的模型路径
+    input_size = 200000  # 根据最大特征长度设定
+    hidden_size = 128
+    num_layers = 2
+
+    # 加载模型
+    model = load_model(model_path, input_size, hidden_size, num_layers)
+
+    # 读取音频文件进行情感预测
+    audio_data, sample_rate = sf.read(voice)
+
+    # 进行情感预测
+    max_length = input_size
+    predicted_value, predicted_class = predict(voice, processor, model, max_length)
+
+    # 输出结果
+    if predicted_value is not None:
+        return f'Predicted value: {predicted_value}, Predicted class: {"Positive" if predicted_class == 1 else "Negative"}'
+    else:
+        return "预测失败，未能处理音频文件。"
 
 # 创建 Gradio 界面
 with gr.Blocks() as demo:
-    gr.Markdown("### 录音功能")
-    
-    with gr.Row():
-        record_button = gr.Audio(label="录音", type="filepath")
-        submit_button = gr.Button("提交录音")
-    
-    message = gr.Textbox(label="消息")
+    gr.Markdown("### 录音与情感分析")
     
+    with gr.Row("音频情感分析"):
+        with gr.Column():
+            record_button = gr.Audio(label="录音", type="filepath")
+            submit_button = gr.Button("提交录音")
+        voice_output = gr.Textbox(label="情感数据")
+
     # 设置提交按钮的回调
-    submit_button.click(record_audio, inputs=record_button, outputs=[message, record_button])
+    submit_button.click(record_audio, inputs=record_button, outputs=voice_output)
+    voice_output.change(voice_sentiment, inputs=voice_output, outputs=voice_output)
 
 # 启动 Gradio 应用
 demo.launch()