#!/usr/bin/env python3 """ 🎙️ Tiny-Audio 单文件绿色独立版 Web 界面 (Standalone Web UI) 特点: - 零项目目录依赖: 模型架构代码已全部内置于本脚本中,不再依赖 tiny_audio 包。 - 跨平台兼容: 无论是在 Windows、Mac (Apple Silicon) 还是 Linux 上均可直接运行。 - 只需携带本文件和 outputs/ 权重目录即可在任意电脑上部署运行。 依赖安装: pip install torch transformers peft gradio soundfile """ import os import sys import time from pathlib import Path import gradio as gr import numpy as np import soundfile as sf import torch from peft import PeftModel from torch import nn from transformers import ( AutoFeatureExtractor, AutoModelForCausalLM, AutoTokenizer, GraniteSpeech5Encoder, PreTrainedTokenizerBase, ) from transformers.models.llama.modeling_llama import LlamaRMSNorm # ============================================================================== # 1. 内置投影层与基座加载逻辑 (完全自包含) # ============================================================================== def _frame_stack_length(length: int | torch.Tensor, k: int) -> int | torch.Tensor: return (length - k) // k + 1 def _frame_stack(x: torch.Tensor, k: int) -> torch.Tensor: batch, seq, dim = x.shape out_len = _frame_stack_length(seq, k) return x[:, : out_len * k, :].reshape(batch, out_len, dim * k) class MLPAudioProjector(nn.Module): def __init__(self, config: object) -> None: super().__init__() encoder_dim: int = getattr(config, "encoder_dim", 1024) llm_dim: int = getattr(config, "llm_dim", 2048) self.k: int = getattr(config, "projector_pool_stride", 1) in_dim = encoder_dim * self.k hidden_dim: int = getattr(config, "projector_hidden_dim", None) or llm_dim self.input_norm = LlamaRMSNorm(in_dim, eps=1e-6) self.linear_1 = nn.Linear(in_dim, hidden_dim) self.act = nn.GELU() self.linear_2 = nn.Linear(hidden_dim, llm_dim) def forward(self, x: torch.Tensor) -> torch.Tensor: x = _frame_stack(x, self.k) x = self.input_norm(x) x = self.linear_1(x) x = self.act(x) return self.linear_2(x) class StandaloneASRModel(nn.Module): def __init__( self, encoder_model_id: str = "ibm-granite/granite-speech-5.0-470m-turboctc-nc", decoder_model_id: str = "Qwen/Qwen3.5-0.8B", device: str = "cuda" if torch.cuda.is_available() else "cpu", dtype: torch.dtype = torch.bfloat16, ): super().__init__() self.device = device self.dtype = dtype print("1/3 加载音频特征提取器与 Granite-Speech-5.0 编码器...") self.feature_extractor = AutoFeatureExtractor.from_pretrained(encoder_model_id) self.encoder = GraniteSpeech5Encoder.from_pretrained( encoder_model_id, torch_dtype=dtype, attn_implementation="sdpa", low_cpu_mem_usage=True, ).to(device=device, dtype=dtype) self.encoder.eval().requires_grad_(False) print("2/3 加载 Qwen 分词器与文本解码器...") self.tokenizer = AutoTokenizer.from_pretrained(decoder_model_id, trust_remote_code=True) if self.tokenizer.pad_token is None: self.tokenizer.pad_token = self.tokenizer.eos_token self.decoder = AutoModelForCausalLM.from_pretrained( decoder_model_id, dtype=dtype, attn_implementation="sdpa", low_cpu_mem_usage=True, trust_remote_code=True, ).to(device=device, dtype=dtype) self.decoder.eval().requires_grad_(False) # 注册