Alex 57a2e24101 Fix SNAC decoding: correct token offset + device attribute ...

- CODE_TOKEN_OFFSET is 10 in decoded text (not 128266 in token ID space)
  because tokenizer.decode() maps 128266 → <custom_token_10>
- Fixed 'SNAC object has no attribute device' — use explicit SNAC_DEVICE
- Added debug logging for pipeline visibility
- Audio now generates correctly: 442KB for "Hello world"

True streaming pipeline verified: text → TextIteratorStreamer →
regex extraction → SNAC decode → PCM bytes. The bottleneck is
Jetson inference speed (~12s for first 42 tokens on a 3B model),
not the streaming infrastructure.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

2026-04-13 16:41:14 -05:00

24 KiB

Raw Blame History

View Raw