Re-export gigaam-v3-rnnt (loom-exporter e6d4e09)

README.md

@@ -42,10 +42,14 @@ import loom
 
 model = loom.Model.from_pretrained("loom-ai-org/gigaam-v3-rnnt-loom")
 
-# Audio is a mono float list at 16 kHz. Long files are windowed for you, and a model that emits
-# timestamps is seeked to where it closed its last segment rather than cut at a fixed stride.
+# Audio is a mono float list at 16 kHz. This model decodes in the one language it was trained for and
+# takes no `language=` argument -- passing one warns and is ignored, because nothing in its decode
+# could act on it.
 result = model.speech2text.infer(audio, timestamps=True)
 print(result.text)
+
+# It emits no timestamp tokens, so `segments` is one span covering the whole clip and
+# `result.timestamped` is False. Check that before treating a start/end as a boundary the model chose.
 for segment in result.segments:
     print(segment.start, segment.end, segment.text)
 ```