Skip to content
View fufuchiu's full-sized avatar
🌴
On vacation
🌴
On vacation
  • 18:08 (UTC +08:00)

Block or report fufuchiu

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
fufuchiu/README.md

Chen Yuxuan

主要使用 Python、NumPy 和 PyTorch,研究从音频输入、模型训练到解码与评测的完整流程。

项目

项目 研究方向 已实现内容
hanstream-asr 语音识别 声学特征、CTC 束搜索与强制对齐、中文英文评测、可训练 GRU 基线
speechloom 端到端语音模型 可微音频编码器、因果解码器、文本/音频联合损失、流式协议与检查点

两个项目都包含命令行工具、可运行示例、输入契约测试和 CPU 模型测试。

当前关注

  • 中文与英文转写的规范化、识别错误分析和可复现评测。
  • 文本 token 与音频 token 的统一训练、模态权重和因果掩码。
  • 有界音频缓冲、UTF-8 增量解码、背压与取消语义。
  • 使用公开接口契约与自动化测试记录实现边界。

Pinned Loading

  1. hanstream-asr hanstream-asr Public

    Speech recognition experiments: log-mel features, CTC decoding, Chinese/English metrics and a trainable baseline.

    Python 1

  2. speechloom speechloom Public

    End-to-end speech model research: waveform encoding, causal decoding, codec tokens, joint losses and streaming.

    Python 31 189

  3. William-Lu-stack/Flawless William-Lu-stack/Flawless Public

    AI SRE AgenticOps for Kubernetes and cloud infrastructure.

    Python 781 165

  4. jasonsuhari/gridbash jasonsuhari/gridbash Public

    Cross-platform terminal grid for running Codex, Claude, Gemini, and other CLI agents side by side.

    Rust 134 5