ASR logging

package.json

@@ -1,6 +1,6 @@
 {
 	"name": "@ztimson/ai-utils",
-	"version": "0.1.6",
+	"version": "0.1.13",
 	"description": "AI Utility library",
 	"author": "Zak Timson",
 	"license": "MIT",

src/ai.ts

@@ -9,17 +9,17 @@ export type AiOptions = LLMOptions & {
 	whisper?: {
 		/** Whisper binary location */
 		binary: string;
-		/** Model */
+		/** Model: `ggml-base.en.bin` */
-		model: WhisperModel;
+		model: string;
-		/** Working directory for models and temporary files */
+		/** Path to models */
 		path: string;
+		/** Path to storage location for temporary files */
+		temp?: string;
 	}
 }
 
-export type WhisperModel = 'tiny' | 'base' | 'small' | 'medium' | 'large';
-
 export class Ai {
-	private downloads: {[key: string]: Promise<void>} = {};
+	private downloads: {[key: string]: Promise<string>} = {};
 	private whisperModel!: string;
 
 	/** Large Language Models */
@@ -27,7 +27,11 @@ export class Ai {
 
 	constructor(public readonly options: AiOptions) {
 		this.llm = new LLM(this, options);
-		if(this.options.whisper?.binary) this.downloadAsrModel(this.options.whisper.model);
+		if(this.options.whisper?.binary) {
+			this.whisperModel = this.options.whisper?.model.endsWith('.bin') ? this.options.whisper?.model : this.options.whisper?.model + '.bin';
+			console.log('constructor: ' + this.options.whisper.model + ' -> ' + this.whisperModel);
+			this.downloadAsrModel();
+		}
 	}
 
 	/**
@@ -36,13 +40,14 @@ export class Ai {
 	 * @param model Whisper model
 	 * @returns {Promise<any>} Extracted text
 	 */
-	async asr(path: string, model?: WhisperModel): Promise<string | null> {
+	async asr(path: string, model: string = this.whisperModel): Promise<string | null> {
 		if(!this.options.whisper?.binary) throw new Error('Whisper not configured');
-		if(!model) model = this.options.whisper.model;
+		const m = await this.downloadAsrModel(model);
-		await this.downloadAsrModel(<string>model);
+		const name = Math.random().toString(36).substring(2, 10) + '-' + path.split('/').pop() + '.txt';
-		const name = Math.random().toString(36).substring(2, 10) + '-' + path.split('/').pop();
+		const output = Path.join(this.options.whisper.temp || '/tmp', name);
-		const output = Path.join(this.options.whisper.path || '/tmp', name);
+		console.log('ASR: ' + this.options.whisper.model + ' -> ' + this.whisperModel);
-		await $`rm -f /tmp/${name}.txt && ${this.options.whisper.binary} -nt -np -m ${this.whisperModel} -f ${path} -otxt -of ${output}`;
+		console.log(`rm -f ${output} && ${this.options.whisper.binary} -nt -np -m ${m} -f ${path} -otxt -of ${output}`);
+		await $`rm -f ${output} && ${this.options.whisper.binary} -nt -np -m ${m} -f ${path} -otxt -of ${output}`;
 		return fs.readFile(output, 'utf-8').then(text => text?.trim() || null)
 			.finally(() => fs.rm(output, {force: true}).catch(() => {}));
 	}
@@ -51,17 +56,24 @@ export class Ai {
 	 * Downloads the specified Whisper model if it is not already present locally.
 	 *
 	 * @param {string} model Whisper model that will be downloaded
-	 * @return {Promise<void>} A promise that resolves once the model is downloaded and saved locally.
+	 * @return {Promise<string>} Absolute path to model file, resolves once downloaded
 	 */
-	async downloadAsrModel(model: string): Promise<void> {
+	async downloadAsrModel(model: string = this.whisperModel): Promise<string> {
 		if(!this.options.whisper?.binary) throw new Error('Whisper not configured');
-		this.whisperModel = Path.join(<string>this.options.whisper?.path, this.options.whisper?.model + '.bin');
+		if(!model.endsWith('.bin')) model += '.bin';
-		if(await fs.stat(this.whisperModel).then(() => true).catch(() => false)) return;
+		const p = Path.join(this.options.whisper.path, model);
+		console.log('Download: ' + p);
+		if(await fs.stat(p).then(() => true).catch(() => false)) {
+			console.log('Exists!');
+			return p;
+		}
 		if(!!this.downloads[model]) return this.downloads[model];
-		this.downloads[model] = fetch(`https://huggingface.co/ggerganov/whisper.cpp/resolve/main/${this.options.whisper?.model}.bin`)
+		this.downloads[model] = fetch(`https://huggingface.co/ggerganov/whisper.cpp/resolve/main/${model}`)
-			.then(resp => resp.arrayBuffer()).then(arr => Buffer.from(arr)).then(async buffer => {
+			.then(resp => resp.arrayBuffer())
-				await fs.writeFile(this.whisperModel, buffer);
+			.then(arr => Buffer.from(arr)).then(async buffer => {
+				await fs.writeFile(p, buffer);
 				delete this.downloads[model];
+				return p;
 			});
 		return this.downloads[model];
 	}