Update app.py

app.py

@@ -66,7 +66,7 @@ PAGE = r"""
 </header>
 <section class="panel">
   <div class="section-head"><div class="step">01</div><div><h2>Source & settings</h2><div class="muted">Choose a recording and describe what you want to isolate.</div></div></div>
-  <div class="file-wrap"><label for="sam-audio-file">Audio file</label><input id="sam-audio-file" type="file" accept="audio/*,.wav,.mp3,.flac,.ogg,.m4a"><div class="muted" style="margin-top:8px">WAV, MP3, FLAC, OGG, or M4A · Recommended: a short clip for the first run</div></div>
+  <div class="file-wrap"><label for="sam-audio-file">Audio file</label><input id="sam-audio-file" type="file" accept=".wav,.mp3,.flac,.ogg,.m4a,audio/wav,audio/mpeg,audio/flac,audio/ogg,audio/mp4"><div class="muted" style="margin-top:8px">WAV, MP3, FLAC, OGG, or M4A · Maximum duration: 2 minutes</div></div>
   <div class="controls">
     <div class="field prompt-field"><label for="sam-prompt">What should be isolated?</label><input id="sam-prompt" type="text" value="a person speaking" placeholder="e.g. a person speaking"></div>
     <div class="field"><label for="sam-provider">Processing device</label><select id="sam-provider"><option value="auto" selected>Automatic</option><option value="webgpu">GPU · WebGPU</option><option value="wasm">CPU · WASM</option></select></div>
@@ -97,6 +97,7 @@ async () => {
   const $ = (id) => root.querySelector("#" + id);
   const MODEL_BASE = "https://huggingface.co/matbee/sam-audio-small-onnx/resolve/main";
   const CACHE_NAME = "sam-audio-webgpu-models-v1";
+  const MAX_AUDIO_SECONDS = 120;
   const MODEL_FILES = {
     encoder: "dacvae_encoder.onnx",
     decoder: "dacvae_decoder.onnx",
@@ -378,6 +379,9 @@ async () => {
     const context = new AudioContextClass();
     try {
       const decoded = await context.decodeAudioData(bytes.slice(0));
+      if (decoded.duration > MAX_AUDIO_SECONDS) {
+        throw new Error("Audio must be 2 minutes or shorter. Selected file is " + formatDuration(decoded.duration) + ".");
+      }
       const offline = new OfflineAudioContext(1, Math.ceil(decoded.duration * 48000), 48000);
       const source = offline.createBufferSource();
       const mono = offline.createBuffer(1, decoded.length, decoded.sampleRate);
@@ -546,7 +550,7 @@ async () => {
     if (!Number.isInteger(steps) || steps < 1 || steps > 16) throw new Error("ODE steps must be between 1 and 16.");
     const audio = await decodeAudio(file);
     const expectedSamples = audio.samples.length;
-    if (expectedSamples > 48000 * 20) throw new Error("For this first prototype, use audio no longer than 20 seconds.");
+    if (expectedSamples > 48000 * MAX_AUDIO_SECONDS) throw new Error("Audio must be 2 minutes or shorter.");
     setStatus("Loading models for " + deviceLabel + "…");
     if (provider === "wasm") {
       setLog("CPU mode selected. ONNX Runtime will use WebAssembly in a background worker where supported, keeping the page responsive. This may take longer than GPU inference.");