Use context managers when reading config.json in VoxCPMModel.from_local()
and VoxCPM2Model.from_local() to prevent file descriptor leaks. Also add
explicit encoding="utf-8" to avoid locale-dependent decode errors.
Closes#235
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Support optional ref_audio samples in finetuning and make runtime device selection explicit while keeping auto fallback behavior consistent. Also ignore the local app override file to avoid accidental commits.
Made-with: Cursor
The previous guard `not text.strip() or not isinstance(text, str)` called
.strip() before verifying that text is actually a string, causing an
AttributeError (e.g. for int input) instead of the intended ValueError.
Swap operand order so isinstance check short-circuits first.
Closes#228
Streaming decode previously re-decoded 4 overlapping patches through
the VAE each step, discarding 75% of the output. Replace with stateful
decode that carries causal conv padding buffers between calls — one
patch in, one patch out, no overlap.
Changes:
- Add StreamingVAEDecoder to audiovae/audio_vae_v2.py — caches
CausalConv1d and CausalTransposeConv1d left-pad state between calls
- AudioVAE.streaming_decode() context manager for clean lifecycle
- _inference yields single-patch latents in streaming mode
- _generate and _generate_with_prompt_cache use StreamingVAEDecoder
Streaming VAE decode time (isolated): 289ms → 148ms (2x faster)
Stateful vs full decode: cosine 1.0000, max diff 0.0005
(more accurate than previous overlap approach at max diff 0.001)
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Add `residual_lm_no_rope` config option in VoxCPMConfig and propagate to MiniCPMModel
- Add `no_rope` field to MiniCPM4Config; make RoPE embedding optional in MiniCPMModel and MiniCPMAttention
- Add `streaming_prefix_len` parameter to generation interface
- Fix non-streaming audio decode in continuation mode to trim leading prefix patches consistently
- Refactor streaming prefix context preparation: distinguish continuation vs. zero-shot via feat_mask trailing bit instead of audio_mask sum
Made-with: Cursor
