lomasub 0.1.2 → 0.1.3

package/README.md

@@ -20,7 +20,7 @@ For a Node.js project, run `npm install lomasub`. For a persistent CLI, run `npm
 ```bash
 lomasub transcribe video.mp4 --output video.srt
 lomasub transcribe video.mp4 --speaker-diarization --srt-max-chars 48 --srt-cue-words 6
-lomasub transcribe video.mp4 --config options.json --no-revise-srt
+lomasub transcribe video.mp4 --config options.json
 lomasub transcribe video.mp4 --no-ffmpeg
 lomasub download <job-id> --output video.srt
 lomasub --help
@@ -42,7 +42,7 @@ When ffmpeg is on `PATH`, audio is extracted into a temporary Matroska audio fil
 }
 ```
 
-Every current transcription config field has a kebab-case flag. Boolean fields support `--name` and `--no-name`. Explicit flags override JSON values, including `false` and `0`. Unset settings use server defaults; the API validates settings and reports retired names. Additional config keys pass through unchanged.
+Supported transcription flags use kebab-case. Use `--promodel pro` (SDK: `config: { promodel: "pro" }`) for word correction before alignment. Revision settings (`revise_srt`, `revise_speakername`, `srt_revision_backend`) are not supported by this CLI/SDK, including through `--config` JSON. Boolean fields support `--name` and `--no-name`. Explicit flags override JSON values, including `false` and `0`. Unset settings use server defaults; the API validates settings and reports retired names. Other additional config keys pass through unchanged.
 
 | Settings | CLI flags |
 | --- | --- |
@@ -50,10 +50,11 @@ Every current transcription config field has a kebab-case flag. Boolean fields s
 | VAD | `--min-vad-duration-seconds`, `--max-vad-duration-seconds`, `--vad-threshold` |
 | Subtitle cues | `--min-srt-duration-ms`, `--srt-max-chars`, `--srt-cue-words` |
 | Diarization | `--speaker-diarization`, `--speaker-local-distance-threshold`, `--speaker-merge-distance-threshold`, `--speaker-clustering-drop-dialogue-percentile`, `--agglomeration-min-appear`, `--agglomolation-group-size` |
-| Revision | `--revise-srt`, `--revise-speakername`, `--srt-revision-backend` (`agy`, `codex`) |
 
 `--filename`, `--language`, and `--duration-seconds` are job metadata, outside config. The original local filename is preserved unless overridden. An explicit duration is forwarded to upload preparation and job creation; duration is not automatically measured.
 
+The server defaults omitted, null, or blank language to `th`; `--language en` overrides it. The Thai hint permits Thai, English, and mixed transcripts: readable English is not discarded because of its script. This is a model hint, not automatic language detection.
+
 Use `--endpoint http://localhost:8080` for another API server. The default is `https://api.lomasub.ai`. Bearer credentials are sent only to the API, never to storage upload/download URLs.
 
 ## SDK

package/cli.js

@@ -17,6 +17,24 @@ for (const [key, type] of Object.entries(TRANSCRIPTION_OPTIONS)) {
   if (type === 'boolean') options[`no-${flag}`] = { type: 'boolean' };
 }
 
+// Display-only production defaults; omitted options still use the API's settings.
+const DEFAULT_HELP = {
+  forcealigner_level: 'default; choices: default, llmsplitting, none',
+  promodel: 'disabled (omitted/null); use pro to enable word correction',
+  min_vad_duration_seconds: '10',
+  max_vad_duration_seconds: '25',
+  vad_threshold: '0.30',
+  min_srt_duration_ms: '1200',
+  srt_max_chars: '48',
+  srt_cue_words: '6',
+  speaker_diarization: 'disabled',
+  speaker_local_distance_threshold: '0.60',
+  speaker_merge_distance_threshold: '0.35',
+  speaker_clustering_drop_dialogue_percentile: '0.02',
+  agglomeration_min_appear: '5',
+  agglomolation_group_size: '300',
+};
+
 function number(value, flag) {
   const parsed = Number(value);
   if (!value.trim() || !Number.isFinite(parsed)) throw new Error(`--${flag} requires a number.`);
@@ -32,17 +50,20 @@ async function main() {
 
 Set LOMA_API_SECRET_KEY before running. Default endpoint: https://api.lomasub.ai
 Options:
-  --endpoint <url>       API endpoint
   --output, -o <path>    Output SRT (default: beside input)
   --overwrite           Replace existing output
   --no-ffmpeg           Upload original without audio extraction
-  --language <code>     Audio language
+  --language <code>     ASR language hint: th, en; server default: th
   --filename <name>     Job display filename
-  --duration-seconds N  Optional media duration hint
   --config <path>       JSON transcription config; explicit flags override it
 
-Transcription options (unset values use server defaults):
-${Object.entries(TRANSCRIPTION_OPTIONS).map(([key, type]) => `  --${key.replaceAll('_', '-')}${type === 'boolean' ? ' / --no-' + key.replaceAll('_', '-') : ' <' + type + '>'}`).join('\n')}`);
+Transcription options:
+Defaults shown are for api.lomasub.ai; omitted options use server settings.
+${Object.entries(TRANSCRIPTION_OPTIONS).map(([key, type]) => {
+  const flag = key.replaceAll('_', '-');
+  const label = `--${flag}${type === 'boolean' ? ` / --no-${flag}` : ` <${type}>`}`;
+  return `  ${label.padEnd(56)}default: ${DEFAULT_HELP[key]}`;
+}).join('\n')}`);
     return;
   }
   const [command, input] = positionals;

package/index.d.ts

@@ -1,4 +1,5 @@
 export interface TranscriptionConfig {
+  promodel?: 'pro' | null;
   forcealigner_level?: 'default' | 'llmsplitting' | 'none';
   min_vad_duration_seconds?: number;
   max_vad_duration_seconds?: number;
@@ -12,9 +13,6 @@ export interface TranscriptionConfig {
   speaker_clustering_drop_dialogue_percentile?: number;
   agglomeration_min_appear?: number;
   agglomolation_group_size?: number;
-  revise_srt?: boolean;
-  revise_speakername?: boolean;
-  srt_revision_backend?: 'agy' | 'codex';
   [key: string]: unknown;
 }
 

package/index.js

@@ -13,6 +13,7 @@ const run = promisify(execFile);
 // Shared with the CLI; validation and transcription defaults belong to the API.
 export const TRANSCRIPTION_OPTIONS = {
   forcealigner_level: 'string',
+  promodel: 'string',
   min_vad_duration_seconds: 'number',
   max_vad_duration_seconds: 'number',
   vad_threshold: 'number',
@@ -25,9 +26,6 @@ export const TRANSCRIPTION_OPTIONS = {
   speaker_clustering_drop_dialogue_percentile: 'number',
   agglomeration_min_appear: 'number',
   agglomolation_group_size: 'number',
-  revise_srt: 'boolean',
-  revise_speakername: 'boolean',
-  srt_revision_backend: 'string',
 };
 
 const MIME_TYPES = {
@@ -69,6 +67,9 @@ export class LomaClient {
   async submitFile(file, options = {}) {
     const { signal, onProgress = () => {}, ffmpeg = true, config, language, duration_seconds } = options;
     signal?.throwIfAborted();
+    for (const key of ['revise_srt', 'revise_speakername', 'srt_revision_backend']) {
+      if (config && Object.hasOwn(config, key)) throw new Error(`config.${key} is not supported by the CLI/SDK.`);
+    }
     const original = resolve(file);
     if (!(await stat(original)).isFile()) throw new Error(`Not a regular file: ${file}`);
     let source = original;
@@ -88,10 +89,12 @@ export class LomaClient {
         }
       }
       signal?.throwIfAborted();
+      const size_bytes = (await stat(source)).size;
       const upload = await this.request('/presigned-url', {
         filename: basename(source),
         content_type: MIME_TYPES[extname(source).toLowerCase()] ?? 'application/octet-stream',
         duration_seconds,
+        size_bytes,
       }, signal);
       if (upload.method !== 'PUT' || !upload.upload_url || !upload.source_url || !upload.headers) {
         throw new Error('Invalid /presigned-url response.');
@@ -100,7 +103,7 @@ export class LomaClient {
       const stream = createReadStream(source);
       try {
         const response = await checkedFetch(upload.upload_url, {
-          method: upload.method, headers: { ...upload.headers, 'Content-Length': String((await stat(source)).size) },
+          method: upload.method, headers: { ...upload.headers, 'Content-Length': String(size_bytes) },
           body: stream, duplex: 'half', signal,
         }, 'Upload');
         await response.arrayBuffer();

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "lomasub",
-  "version": "0.1.2",
+  "version": "0.1.3",
   "description": "Lomasub cli is a command-line tool for creating subtitles from local audio or video in Node.js or the terminal, using lomasub.ai cloud service. ",
   "type": "module",
   "engines": { "node": ">=20" },