VoxCPM checkpoints default to bfloat16. Following commit e4e0496 which
added MPS device routing, running with `device=mps` selects bf16 on
Apple Silicon. On Metal, bf16 introduces enough numerical drift in the
diffusion AR loop that the synthesized audio is glitched and trips the
model's badcase detector, which retries until the per-call retry budget
is exhausted. Effectively MPS support is unusable in the default config.
This patch adds a single helper, `pick_runtime_dtype(device, dtype)`,
that promotes any low-precision dtype to float32 when the resolved
device is `mps`. CUDA and CPU paths are untouched. An opt-out env var
`VOXCPM_MPS_DTYPE` lets users force a specific dtype on MPS once future
PyTorch / macOS releases improve bf16 stability.
Both VoxCPMModel and VoxCPM2Model adopt the helper in their __init__,
replacing what would otherwise be duplicated inline checks.
Verified locally on Apple M5 Max, PyTorch 2.11, macOS 15:
- VoxCPM2 (2B): clean output, RTF ~0.78 steady state
- VoxCPM 0.5B: clean output, RTF ~0.92
- No badcase retries fired in any test
- VOXCPM_MPS_DTYPE=bfloat16 round-trips and reproduces the original
glitched output, confirming the override path.
Move generator close handling into a shared utility and wire the core generation pipeline through it so partially-consumed prompt cache generators are cleaned up consistently across both model variants and the public VoxCPM wrapper.
Made-with: Cursor
Factor repeated next-and-close patterns into a shared helper in both VoxCPM model variants so non-streaming inference cleans up generators consistently while keeping the issue reference close to the workaround.
Made-with: Cursor
Use an explicit broadcastable attention mask shape during MiniCPM incremental decoding so CPU runtimes avoid a PyTorch SDPA dimension error without changing attention semantics.
Made-with: Cursor
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
- 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
oumnya