update

Author: wenerme

notes/ai/README.md

@@ -10,6 +10,24 @@ title: AI
 
 - 规则系统、专家系统、机器学习
 
+---
+
+- fundamentals
+  - [机器学习](./ml/README.md)
+  - Deep Learning
+- models
+  - [LLM](./llm/README.md)
+    - [GPT](./gpt/README.md)
+  - [GAN](./gan/README.md)
+  - Diffusion
+- domains
+  - [OCR](./ocr/README.md)
+  - [NLP](./nlp/README.md)
+  - [TTS](./tts/README.md)
+  - [ASR](./asr/README.md)
+- services
+  - OpenAI
+
 ## 解释
 
 - 常见子领域

notes/ai/ai-faq.md

@@ -29,3 +29,10 @@ tags:
 - RAQ - retrieval-augmented generation - 检索增强生成
 - 参考
   - https://research.ibm.com/blog/retrieval-augmented-generation-RAG
+
+## STT vs ASR
+
+- STT: Speech to Text - 语音转文本
+  - 产品功能描述
+- ASR: Automatic Speech Recognition - 自动语音识别
+  - 技术

notes/ai/ai-glossary.md

@@ -40,6 +40,8 @@ tags:
 | en               | cn       |
 | ---------------- | -------- |
 | Stable Diffusion | 稳定扩散 |
+| Speech Synthesis | 语音合成 |
+| Voice Synthesis  | 语音合成 |
 
 ## LLM 参数
 

notes/ai/asr.md renamed to notes/ai/asr/README.md

@@ -5,6 +5,7 @@ tags:
 
 # ASR
 
+- ASR - Automatic Speech Recognition - 自动语音识别
 - [FunASR](./funasr.md)
 - [Whisper](./whisper.md)
 - Kaldi

notes/ai/funasr.md renamed to notes/ai/asr/funasr.md

@@ -36,30 +36,30 @@ bash run_server.sh \
 ## Protocol
 
 ```ts
-  interface OfflineRequestMessage {
-    mode: 'offline';
-    wav_name: string;
-    wav_format: string | 'pcm' | 'mp3' | 'mp4';
-    is_speaking: boolean; // false -> 断句尾点，例如，vad切割点，或者一条wav结束
-    audio_fs?: number; // pcm 采样率
-    hotwords?: Record<string, number>; // 热词
-    itn?: boolean; // 默认 true
-  }
+interface OfflineRequestMessage {
+  mode: 'offline';
+  wav_name: string;
+  wav_format: string | 'pcm' | 'mp3' | 'mp4';
+  is_speaking: boolean; // false -> 断句尾点，例如，vad切割点，或者一条wav结束
+  audio_fs?: number; // pcm 采样率
+  hotwords?: Record<string, number>; // 热词
+  itn?: boolean; // 默认 true
+}
 
-  interface ResponseMessage {
-    mode: 'offline';
-    wav_name: string;
-    text: string;
-    is_final: boolean;
-    timestamp?: number[][]; // 时间戳 "[[100,200], [200,500]]"(ms)
-    stamp_sents?: {
-      text_seg: string; // 正 是 因 为
-      punc: string; // ,
-      start: number;
-      end: number;
-      ts_list: number[][]; // [[430,670],[670,810],[810,1030],[1030,1130]]
-    }[];
-  }
+interface ResponseMessage {
+  mode: 'offline';
+  wav_name: string;
+  text: string;
+  is_final: boolean;
+  timestamp?: number[][]; // 时间戳 "[[100,200], [200,500]]"(ms)
+  stamp_sents?: {
+    text_seg: string; // 正 是 因 为
+    punc: string; // ,
+    start: number;
+    end: number;
+    ts_list: number[][]; // [[430,670],[670,810],[810,1030],[1030,1130]]
+  }[];
+}
 ```
 
 - mode

notes/ai/whisper.md renamed to notes/ai/asr/whisper.md

@@ -29,8 +29,11 @@ title: ollama
 ```bash
 brew install ollama # macOS brew
 
-OLLAMA_FLASH_ATTENTION=1 ollama serve # 启动服务端
-ollama run mistral                    # 运行模型
+# 启动服务端
+# OLLAMA_KV_CACHE_TYPE 0.5+
+OLLAMA_FLASH_ATTENTION=1 OLLAMA_KV_CACHE_TYPE=q4_0 ollama serve
+
+ollama run mistral # 运行模型
 ollama list
 
 # https://hub.docker.com/r/ollama/ollama

notes/ai/dalle.md renamed to notes/ai/gan/dalle.md

@@ -138,6 +138,9 @@ tags:
     - XCiT
     - DINO - Self-Supervised Vision Transformers
     - PyTorch code for Vision Transformers training with the Self-Supervised learning method DINO
+  - GOT - Generic Object Tracking
+    - [GOT-10k](http://got-10k.aitestunion.com/)
+    - [GOT-10k: A Large High-Diversity Benchmark for Generic Object Tracking in the Wild](https://arxiv.org/abs/1810.11981)
 - audio/music/speech/voice/tts
   - [microsoft/muzic](https://github.com/microsoft/muzic)
   - [yl4579/StyleTTS2](https://github.com/yl4579/StyleTTS2)

notes/ai/llm/ollama.md

@@ -9,6 +9,7 @@ tags:
   - Apache-2.0
   - by Baidu
   - 飞桨 - PADDLE -> PArallel Distributed Deep LEarning
+  - 通用框架，但 Paddle 主要中文 OCR, NLP 做得好
 - 参考
   - https://www.paddlepaddle.org.cn/
   - [PaddlePaddle/PaddleHub](https://github.com/PaddlePaddle/PaddleHub)
@@ -22,6 +23,7 @@ pip install paddlepaddle
 pip install paddlepaddle-gpu
 
 # Docker
+# 百度镜像 registry.baidubce.com/paddlepaddle/paddle:3.0.0b1
 docker run --rm -it -v $PWD:/host --entrypoint /host --name paddle paddlepaddle/paddle /bin/bash
 ```