@audio/neural-separate 0.6.0 → 0.7.0

package/README.md

@@ -277,6 +277,7 @@ let vocals = complex.vocals.map(ch => istft(ch, { length: left.length }))
 | `window` / `normalized` / `frames` | the preset's | `'complex'`: the model's STFT window (`'ones'`, torch.stft's window=None, or `'hann'`), its 1/√n scaling, its frames per segment when the graph does not declare them |
 | `targetRate` | the preset's rate, else the input rate | resample to the model's rate for inference; stems are resampled back to the input rate |
 | `device` | — | passed through to `@audio/neural-runtime`'s `load()` as `backend` |
+| `wasmPaths` | — | where onnxruntime-web's `.wasm` files are served, passed through to `load()`: needed where ORT itself comes from a CDN that rebuilds it (esm.sh), e.g. `'https://cdn.jsdelivr.net/npm/onnxruntime-web@1.30.0/dist/'` |
 | `dtype` | `'float32'` | only `'float32'` tensor marshalling is implemented; anything else throws |
 | `progress` | — | `({ chunk, totalChunks }) => {}` |
 | `session` | — | overrides `@audio/neural-runtime`'s `load()` — for tests, or a custom ORT setup |

package/index.d.ts

@@ -131,6 +131,9 @@ export interface SeparateOptions {
 	hop?: number
 	/** passed through to @audio/neural-runtime's load() as `backend` */
 	device?: string
+	/** where onnxruntime-web's .wasm files are served (a URL prefix, or a file → URL map), passed through to
+	 *  @audio/neural-runtime's load(): for an ORT build loaded from a CDN that rebuilds it (esm.sh) */
+	wasmPaths?: string | Record<string, string>
 	/** only 'float32' is implemented; anything else throws */
 	dtype?: 'float32'
 	progress?: (p: { chunk: number; totalChunks: number }) => void

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@audio/neural-separate",
-  "version": "0.6.0",
+  "version": "0.7.0",
   "description": "Source separation (stems): a song's by SCNet (MIT weights), Hybrid Transformer Demucs, Open-Unmix with multichannel Wiener refinement; a soundtrack's dialogue, music and effects by MRX (MIT weights) and TIGER (Apache-2.0); model-agnostic ONNX",
   "type": "module",
   "sideEffects": false,
@@ -29,7 +29,7 @@
     "NOTICE"
   ],
   "dependencies": {
-    "@audio/neural-runtime": "^0.1.1",
+    "@audio/neural-runtime": "^0.2.0",
     "@audio/resample-sinc": "^1.1.2",
     "fourier-transform": "^2.4.1"
   },

package/separate.js

@@ -30,7 +30,7 @@ import resampleSinc from '@audio/resample-sinc'
 import { load as neuralLoad, tensor, fetchModel, fetchJson, backends } from '@audio/neural-runtime'
 
 const PI2 = Math.PI * 2
-const isNode = typeof process !== 'undefined' && !!process.versions?.node
+const isNode = globalThis.process?.release?.name === 'node'  // Node, Bun, Deno: not a process polyfill (esm.sh's, a bundler's), whose versions.node is set
 
 // ---------------------------------------------------------------- STFT/iSTFT
 
@@ -575,7 +575,7 @@ function loader(opts, preset) {
 		let s = own && await own
 		if (s) return s
 		let spec = g.sha256 && !g.spec.startsWith('file:') ? await checked(g.spec, g.sha256) : g.spec
-		return neuralLoad(spec, { backend: await device, sessionOptions })
+		return neuralLoad(spec, { backend: await device, sessionOptions, wasmPaths: opts.wasmPaths })
 	}
 }