82d77d445c
fix: decode chunksize for audiovae_v2
2026-04-08 16:31:36 +08:00
df38f0a167
update readme for modelscope download
2026-04-08 11:29:19 +08:00
0c2cf23617
Update app.py UI, adjust streaming_prefix_len, remove legacy docs
...
- Refine app.py: Ultimate Cloning naming, NFE slider, i18n polish
- Change streaming_prefix_len default from 3 to 4 for smoother decoding
- Remove legacy docs/ directory (migrated to ReadTheDocs)
Made-with: Cursor
2026-04-03 18:42:41 +08:00
30c300cfe8
adjust default cfg range
2026-04-02 18:14:35 +08:00
addee2c550
surport voxcpm2 cli
2026-04-01 21:15:55 +08:00
42c428164c
feat: add no_rope support for residual LM and fix streaming continuation decoding
...
- 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
2026-03-31 17:07:33 +08:00
d9cf376e16
update voxcpm2
2026-03-31 11:50:37 +08:00
8df79de636
fix: use specific exceptions instead of bare except
...
- lora_ft_webui.py: except (JSONDecodeError, OSError) for config file
- voxcpm.py: except ImportError for triton availability check
2026-02-24 22:19:45 +00:00
8f3a91cac8
cli: improve argument validation and help text for VoxCPM CLI
2026-01-20 14:33:58 +05:30
e8dd956fc2
Print all log messages to stderr instead of stdout
2026-01-12 15:30:45 +08:00
f2e203d5e2
print debug messages to stderr instead of stdout
2026-01-09 20:05:52 +02:00
de11c6a8cb
OPTIMIZE: Improve sample length computation by using batch column access
2025-12-20 06:32:39 +07:00
ee5f2567ac
FIX:When a prompt is present, concatenate two patches as the context for VAE decoding
2025-12-15 20:37:02 +08:00
b3a2d95fec
FIX:When a prompt is present, concatenate two patches as the context for VAE decoding
2025-12-15 20:35:46 +08:00
a266c0a88d
add lora funetine webUI; optimize lora save and load logic
2025-12-09 21:34:39 +08:00
400f47a516
Modify lora inference api
2025-12-05 22:22:13 +08:00
b1f7593ae0
Update: default no denoise & normalize
2025-12-05 22:16:27 +08:00
6a5e713698
fix: streaming mode
2025-12-05 22:06:15 +08:00
3443dbb212
Update: VoxCPM1.5 and fine-tuning supprt
2025-12-05 21:04:51 +08:00
2eb4d39719
FX: Add MPS support
2025-09-28 21:06:35 +08:00
5c5da0dbe6
Add a streaming API for VoxCPM
2025-09-19 16:56:11 -04:00
996c69a1a8
add prompt-file option to set prompt text
2025-09-19 12:53:23 +08:00
dc6b6d1d1c
Fx: capture compile error on Windows
2025-09-18 19:23:13 +08:00
cef6aefb3d
remove \n from input text
2025-09-18 14:57:45 +08:00
1a46c5d1ad
update README
2025-09-18 14:53:37 +08:00
5257ec3dc5
FX: noise point
2025-09-18 14:50:01 +08:00
e5bcb735f0
Remove segment text logic
2025-09-18 12:02:37 +08:00
639b2272ab
update README
2025-09-17 19:34:08 +08:00
7e8f754ba1
update README
2025-09-17 19:33:37 +08:00
032c7fe403
capture torch compile error
2025-09-17 18:09:09 +08:00
605ac2d8e4
Replace the text normalization library
2025-09-16 22:16:40 +08:00
436e8cd6e5
set default repo id
2025-09-16 16:52:42 +08:00
11574ae93d
surport load model from local path
2025-09-16 16:46:44 +08:00
081845b35b
FX: readme description
2025-09-16 13:26:14 +08:00
272b8ffbf6
init
2025-09-16 11:46:47 +08:00
Labmem-Zhouyx