update

app.py

@@ -0,0 +1,39 @@
+import gradio as gr
+from transformers import pipeline
+import os
+
+# 加载模型
+pipe = pipeline(
+    task="automatic-speech-recognition",
+    model="fj11/whisper-ja-zh-tiny",
+    return_timestamps=True,
+    generate_kwargs={"task": "translate", "language": "japanese"}
+)
+
+MAX_FILE_SIZE_MB = 10
+
+def transcribe(audio_path):
+    if audio_path is None:
+        return "请上传音频文件"
+
+    # 检查文件大小
+    file_size_mb = os.path.getsize(audio_path) / (1024 * 1024)
+    if file_size_mb > MAX_FILE_SIZE_MB:
+        return f"❌ 文件太大：{file_size_mb:.2f} MB，最大只支持 {MAX_FILE_SIZE_MB} MB"
+
+    # 执行转录
+    result = pipe(audio_path)
+    return result["text"]
+
+# Gradio UI
+demo = gr.Interface(
+    fn=transcribe,
+    inputs=gr.Audio(source="upload", type="filepath", label="上传日语音频文件（≤10MB）"),
+    outputs=gr.Textbox(label="翻译后的中文文本"),
+    title="🎙️ Whisper ja→zh 语音翻译模型",
+    description="上传最大 10MB 的日语语音，输出中文翻译结果。",
+    allow_flagging="never"
+)
+
+if __name__ == "__main__":
+    demo.launch()

requirements.txt

@@ -0,0 +1,18 @@
+certifi==2025.4.26
+charset-normalizer==3.4.2
+filelock==3.18.0
+fsspec==2025.5.1
+hf-xet==1.1.3
+huggingface-hub==0.33.0
+idna==3.10
+numpy==2.3.0
+packaging==25.0
+PyYAML==6.0.2
+regex==2024.11.6
+requests==2.32.4
+safetensors==0.5.3
+tokenizers==0.21.1
+tqdm==4.67.1
+transformers==4.52.4
+typing_extensions==4.14.0
+urllib3==2.4.0