Freeze independent English German speech and boundary validation inputs

tools/speech-eval/test_prepare_validation.py

@@ -0,0 +1,45 @@
+import tempfile
+import unittest
+import wave
+from pathlib import Path
+
+from prepare_validation import write_wav
+
+
+class PreparationTests(unittest.TestCase):
+    def test_known_padding_does_not_change_source_samples(self):
+        with tempfile.TemporaryDirectory() as directory:
+            path = Path(directory) / "clip.wav"
+            samples = b"\x01\x00" * 16000
+            write_wav(path, samples, 5000)
+            with wave.open(str(path), "rb") as clip:
+                self.assertEqual(clip.getnframes(), 96000)
+                self.assertEqual(clip.readframes(80000), bytes(160000))
+                self.assertEqual(clip.readframes(16000), samples)
+
+    def test_full_source_over_budget_is_rejected(self):
+        with tempfile.TemporaryDirectory() as directory:
+            with self.assertRaises(ValueError):
+                write_wav(Path(directory) / "clip.wav", bytes(960000), 5000)
+
+    def test_existing_preparation_cannot_be_overwritten(self):
+        with tempfile.TemporaryDirectory() as directory:
+            path = Path(directory) / "clip.wav"
+            path.write_bytes(b"original")
+            with self.assertRaises(ValueError):
+                write_wav(path, bytes(32000))
+            self.assertEqual(path.read_bytes(), b"original")
+
+    def test_odd_pcm_is_rejected(self):
+        with tempfile.TemporaryDirectory() as directory:
+            with self.assertRaises(ValueError):
+                write_wav(Path(directory) / "clip.wav", b"\x00")
+
+    def test_explicit_seam_budget_is_bounded(self):
+        with tempfile.TemporaryDirectory() as directory:
+            path = Path(directory) / "seam.wav"
+            write_wav(path, bytes(32000 * 35), maximum_ms=45000)
+            with wave.open(str(path), "rb") as clip:
+                self.assertEqual(clip.getnframes(), 16000 * 35)
+            with self.assertRaises(ValueError):
+                write_wav(Path(directory) / "oversized.wav", bytes(32000), maximum_ms=45001)