feat: Add per-segment language detection and dual output files

- Add whatlang for real-time language detection per segment
- Generate .asr.json (basic) and .asrx.json (with language labels)
- Add auto-save progress with configurable interval
- Add resume functionality for interrupted transcriptions
- Add Music/Empty detection and statistics
- Update progress display with unified format
- Add comprehensive Chinese README with usage documentation

Cargo.lock

@@ -2,6 +2,18 @@
 # It is not intended for manual editing.
 version = 4
 
+[[package]]
+name = "ahash"
+version = "0.8.12"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "5a15f179cd60c4584b8a8c596927aadc462e27f2ca70c04e0071964a73ba7a75"
+dependencies = [
+ "cfg-if",
+ "once_cell",
+ "version_check",
+ "zerocopy",
+]
+
 [[package]]
 name = "aho-corasick"
 version = "1.1.4"
@@ -11,6 +23,12 @@ dependencies = [
  "memchr",
 ]
 
+[[package]]
+name = "allocator-api2"
+version = "0.2.21"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "683d7910e743518b0e34f1186f92494becacb047c7b6bf616c96772180fef923"
+
 [[package]]
 name = "anstream"
 version = "0.6.21"
@@ -270,6 +288,16 @@ version = "0.3.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "0cc23270f6e1808e30a928bdc84dea0b9b4136a8bc82338574f23baf47bbd280"
 
+[[package]]
+name = "hashbrown"
+version = "0.14.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "e5274423e17b7c9fc20b6e7e208532f9b19825d82dfd615708b70edd83df41f1"
+dependencies = [
+ "ahash",
+ "allocator-api2",
+]
+
 [[package]]
 name = "heck"
 version = "0.5.0"
@@ -315,6 +343,12 @@ dependencies = [
  "either",
 ]
 
+[[package]]
+name = "itoa"
+version = "1.0.17"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "92ecc6618181def0457392ccd0ee51198e065e016d1d527a7ac1b6dc7c1f09d2"
+
 [[package]]
 name = "lazy_static"
 version = "1.5.0"
@@ -525,7 +559,11 @@ dependencies = [
  "anyhow",
  "clap",
  "ffmpeg-next",
+ "lazy_static",
  "ndarray",
+ "serde",
+ "serde_json",
+ "whatlang",
  "whisper-rs",
  "whisper-rs-sys",
 ]
@@ -555,6 +593,49 @@ dependencies = [
  "windows-sys 0.59.0",
 ]
 
+[[package]]
+name = "serde"
+version = "1.0.228"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9a8e94ea7f378bd32cbbd37198a4a91436180c5bb472411e48b5ec2e2124ae9e"
+dependencies = [
+ "serde_core",
+ "serde_derive",
+]
+
+[[package]]
+name = "serde_core"
+version = "1.0.228"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "41d385c7d4ca58e59fc732af25c3983b67ac852c1a25000afe1175de458b67ad"
+dependencies = [
+ "serde_derive",
+]
+
+[[package]]
+name = "serde_derive"
+version = "1.0.228"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d540f220d3187173da220f885ab66608367b6574e925011a9353e4badda91d79"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn",
+]
+
+[[package]]
+name = "serde_json"
+version = "1.0.149"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "83fc039473c5595ace860d8c4fafa220ff474b3fc6bfdb4293327f1a37e94d86"
+dependencies = [
+ "itoa",
+ "memchr",
+ "serde",
+ "serde_core",
+ "zmij",
+]
+
 [[package]]
 name = "shlex"
 version = "1.3.0"
@@ -596,6 +677,22 @@ version = "0.2.15"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "accd4ea62f7bb7a82fe23066fb0957d48ef677f6eeb8215f372f52e48bb32426"
 
+[[package]]
+name = "version_check"
+version = "0.9.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0b928f33d975fc6ad9f86c8f283853ad26bdd5b10b7f1542aa2fa15e2289105a"
+
+[[package]]
+name = "whatlang"
+version = "0.16.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "471d1c1645d361eb782a1650b1786a8fb58dd625e681a04c09f5ff7c8764a7b0"
+dependencies = [
+ "hashbrown",
+ "once_cell",
+]
+
 [[package]]
 name = "which"
 version = "4.4.2"
@@ -716,3 +813,29 @@ name = "windows_x86_64_msvc"
 version = "0.52.6"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "589f6da84c646204747d1270a2a5661ea66ed1cced2631d546fdfb155959f9ec"
+
+[[package]]
+name = "zerocopy"
+version = "0.8.42"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f2578b716f8a7a858b7f02d5bd870c14bf4ddbbcf3a4c05414ba6503640505e3"
+dependencies = [
+ "zerocopy-derive",
+]
+
+[[package]]
+name = "zerocopy-derive"
+version = "0.8.42"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "7e6cc098ea4d3bd6246687de65af3f920c430e236bee1e3bf2e441463f08a02f"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn",
+]
+
+[[package]]
+name = "zmij"
+version = "1.0.21"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b8848ee67ecc8aedbaf3e4122217aff892639231befc6a1b58d29fff4c2cabaa"

Cargo.toml

@@ -22,6 +22,10 @@ anyhow = "1.0"
 
 # 可選：如果 whisper-rs 需要額外的數學運算支持
 ndarray = "0.15"
+serde = { version = "1.0", features = ["derive"] }
+serde_json = "1.0"
+lazy_static = "1.4"
+whatlang = "0.16"
 
 
 

README.md

@@ -4,21 +4,25 @@
 
 ## 功能特性
 
-- **高效音頻提取**：利用 FFmpeg 直接從影片或音頻檔案中提取並重採樣為 Whisper 所需的格式 (16kHz, Mono, f32)。
+- **高效音頻提取**：利用 FFmpeg 直接從影片或音頻檔案中提取並重採樣為 Whisper 所需的格式 (16kHz, Mono, f32)
-- **精準轉寫**：基於 OpenAI Whisper 模型，提供高精度的語音轉文字功能。
+- **精準轉寫**：基於 OpenAI Whisper 模型，提供高精度的語音轉文字功能
-- **時間碼支援**：自動產生精確到毫秒的逐字稿時間戳。
+- **時間碼支援**：自動產生精確到毫秒的逐字稿時間戳，格式為 `HH:MM:SS.mmm(fXX)` (25fps)
-- **語言自動檢測**：若未指定語言，可自動偵測輸入音頻的語言。
+- **語言自動檢測**：若未指定語言，可自動偵測輸入音頻的語言
-- **優化進度顯示**：在轉寫過程中提供即時的處理進度、耗時與預估剩餘時間。
+- **優化進度顯示**：在轉寫過程中提供即時的處理進度、耗時與預估剩餘時間
+- **自動存檔**：支援定期自動存檔，避免長時間轉寫因意外中斷而遺失進度
+- **中斷續處理**：支援從上次中斷點繼續處理
+- **語言分段檢測**：自動檢測每段文字的語言類型，生成帶語言標籤的逐字稿
+- **特殊內容識別**：自動識別 Music (音樂) 和 Empty (空文字) 分段
 
 ## 前置需求
 
 在編譯與執行前，請確保系統已安裝以下環境：
 
-1. **Rust 環境**：請安裝 [Rustup](https://rustup.rs/)。
+1. **Rust 環境**：請安裝 [Rustup](https://rustup.rs/)
-2. **FFmpeg**：系統必須安裝 FFmpeg 開發庫。
+2. **FFmpeg**：系統必須安裝 FFmpeg 開發庫
    - macOS: `brew install ffmpeg`
    - Ubuntu/Debian: `sudo apt install libavcodec-dev libavformat-dev libavutil-dev libswresample-dev`
-3. **Whisper 模型**：請準備 Whisper 的 `.bin` 模型檔案 (例如 `ggml-base.bin`)，並放置於 `models/` 目錄中。
+3. **Whisper 模型**：請準備 Whisper 的 `.bin` 模型檔案，並放置於 `models/` 目錄中
 
 ## 編譯與安裝
 
@@ -33,7 +37,7 @@ cargo build --release
 
 ## 使用方式
 
-執行程式時，需指定輸入檔案路徑及模型路徑：
+### 基本使用
 
 ```bash
 ./target/release/rust-scribe <input_file> --model models/<your-model.bin>
@@ -41,33 +45,148 @@ cargo build --release
 
 ### 參數說明
 
-- `<input_file>`: 欲轉寫的影片或音頻檔案路徑 (位置參數)。
+| 參數 | 說明 | 必填 |
-- `-m, --model <MODEL_PATH>`: Whisper 模型檔案路徑 (必填)。
+|------|------|------|
-- `-l, --language <LANG>`: 指定轉寫語言 (例如 `zh`, `en`)。若不指定，系統將自動偵測 (選填)。
+| `<input_file>` | 欲轉寫的影片或音頻檔案路徑 | ✅ |
-- `-v, --verbose`: 開啟詳細轉寫進度輸出 (選填)。
+| `-m, --model <MODEL_PATH>` | Whisper 模型檔案路徑 | ✅ |
+| `-l, --language <LANG>` | 指定轉寫語言 (例如 `zh`, `en`)。若不指定將自動偵測 | ❌ |
+| `-v, --verbose` | 開啟詳細轉寫進度輸出 | ❌ |
+| `--save-interval <N>` | 每 N 個分段自動存檔一次 (預設: 100) | ❌ |
+| `--max-duration <秒>` | 限制處理的最大時長（用於測試） | ❌ |
 
-**使用範例**：
+### 使用範例
 
 ```bash
-# 指定使用 base 模型，自動檢測語言
+# 基本使用，自動檢測語言，每 10 個分段存檔
-cargo run --release -- video.mp4 --model models/ggml-base.bin
+cargo run --release -- video.mp4 --model models/ggml-base.bin --save-interval 10
 
-# 指定使用中文進行轉寫
+# 指定中文轉寫
 cargo run --release -- lecture.mkv --model models/ggml-base.bin --language zh
+
+# 限制處理前 60 秒（用於測試）
+cargo run --release -- video.mp4 --model models/ggml-base.bin --max-duration 60
 ```
 
+## 輸出檔案
+
+程式會生成兩個輸出檔案：
+
+### 1. `.asr.json` - 基本逐字稿
+包含基本的轉寫結果：
+```json
+{
+  "input_file": "video.mp4",
+  "language": "English",
+  "segments": [
+    {
+      "start": "00:00:05.120(f03)",
+      "end": "00:00:08.560(f14)",
+      "text": "Hello everyone",
+      "language": "English"
+    }
+  ]
+}
+```
+
+### 2. `.asrx.json` - 帶語言檢測的逐字稿
+包含每段文字的語言檢測結果：
+```json
+{
+  "input_file": "video.mp4",
+  "segments": [
+    {
+      "start": "00:00:05.120(f03)",
+      "end": "00:00:08.560(f14)",
+      "text": "Hello everyone",
+      "language": "English",
+      "confidence": 0.98
+    },
+    {
+      "start": "00:00:10.000(f00)",
+      "end": "00:00:13.000(f00)",
+      "text": "[Music]",
+      "language": "Music",
+      "confidence": 1.0
+    }
+  ]
+}
+```
+
+## 進度顯示說明
+
+轉寫過程中會顯示即時進度：
+
+```
+═══════════════════════════════════════════════════════════
+🎙️  Transcribing (this may take a few minutes)...
+💡  Auto-saving every 10 segments
+📋 Legend:
+   P = Processed (已處理分段數)
+   A = ASR saved (.asr.json 已存檔數)
+   X = Lang detect saved (.asrx.json 已存檔數)
+═══════════════════════════════════════════════════════════
+
+🔄 Progress: [71:05/114:39] 62.0% | Elapsed: 03:04 | Remaining: 01:54 | P:1112 A:1110 X:1110 | English:500 Unknown:52 Music:58
+```
+
+### 進度列格式說明
+
+- **時間進度**：`[已處理時間/總時長] 完成百分比`
+- **時間統計**：`Elapsed: 已耗時 | Remaining: 預估剩餘時間`
+- **分段統計**：`P:已處理數 A:ASR存檔數 X:語言檢測存檔數`
+- **語言統計**：各語言類型的分段數量（依序顯示）
+
+### 特殊類型標籤
+
+- **Music**：音樂或背景音效段落
+- **Empty**：空文字或純空白段落
+- **Unknown**：語言識別置信度低於 0.5 的段落
+
+## 中斷續處理
+
+程式支援中斷後繼續處理：
+
+1. 當程式偵測到已存在的輸出檔案時，會詢問是否繼續
+2. 選擇 `[C] Continue` 會從上次中斷點繼續
+3. 選擇 `[R] Restart` 會刪除舊檔案重新開始
+
+兩個檔案（`.asr.json` 和 `.asrx.json`）會同步處理。
+
+## 語言檢測說明
+
+使用 [whatlang](https://github.com/greyblake/whatlang-rs) 函式庫進行語言檢測：
+
+- **置信度 ≥ 0.5**：顯示檢測到的語言名稱
+- **置信度 < 0.5**：標註為 "Unknown"
+- **Music**：自動識別包含 [Music] 或 (music) 標記的段落
+- **Empty**：空文字或純空白段落
+
 ## 專案結構
 
 ```
 rust-scribe/
 ├── src/
-│   └── main.rs           # 核心邏輯 (音頻處理、Whisper 轉寫、CLI 介面)
+│   └── main.rs           # 核心邏輯
-├── models/               # 存放 Whisper 模型檔案
+├── models/               # Whisper 模型檔案
-├── Cargo.toml            # 專案依賴與配置
+├── Cargo.toml            # 專案配置
+├── Cargo.lock            # 依賴鎖定
+├── README.md             # 使用文檔
+├── AGENTS.md             # 開發者規範
 └── .cargo/
-    └── config.toml       # Cargo 編譯配置
+    └── config.toml       # Cargo 配置
 ```
 
 ## 開發者規範
 
 請參閱 `AGENTS.md` 了解詳細的代碼風格、編譯與測試指南。
+
+## 許可證
+
+MIT License
+
+## 致謝
+
+- [Whisper.cpp](https://github.com/ggerganov/whisper.cpp) - OpenAI Whisper 的 C++ 實現
+- [FFmpeg](https://ffmpeg.org/) - 音頻處理函式庫
+- [whisper-rs](https://github.com/tazz4843/whisper-rs) - Whisper.cpp 的 Rust 綁定
+- [whatlang](https://github.com/greyblake/whatlang-rs) - 自然語言檢測函式庫