Pine/VoxCPM
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Commit Graph

  • 2e4c601d1d - 修复路径错误 main Pine 2026-05-06 14:58:46 +08:00
  • 525ebc65a3 - 修正一个本地模型使用 Pine 2026-05-06 14:28:36 +08:00
  • 564b98b2d5 - 自部署单独用支持：给添哥 Pine 2026-05-06 13:41:26 +08:00
  • 19b6bf7590 fix: handle LoRA rank mismatch during inference in lora_ft_webui liuxin 2026-04-28 10:52:57 +08:00
  • 86bff0fc82 Merge pull request #253 from SuperMarioYL/feat/validate-training-data ZGY 2026-04-27 21:09:41 +08:00
  • dd7b78f2c0 refactor(cli): defer soundfile and voxcpm.core imports to inference commands supermario_leo 2026-04-25 05:09:23 +08:00
  • 29577d57f8 test: fix test_cli_validate_exit_code to use --manifest flag and assert specific exit code supermario_leo 2026-04-24 10:15:57 +08:00
  • 4509becfde fix: address four validation correctness issues from review supermario_leo 2026-04-22 05:06:35 +08:00
  • cd79a647fa Merge pull request #263 from Oumnya/fix/mps-bf16-dtype ZGY 2026-04-21 18:49:48 +08:00
  • 96d605b9de fix(mps): align VOXCPM_MPS_DTYPE override set with get_dtype parser Oumnya 2026-04-21 18:24:53 +08:00
  • a9b03a768c Merge pull request #277 from gluttony-10/main ZGY 2026-04-21 17:11:42 +08:00
  • 77f847fcba Merge pull request #268 from shaun0927/fix/lora-weights-only ZGY 2026-04-21 16:55:42 +08:00
  • d3cc88722c feat: enhance control text processing in VoxCPMDemo gluttony-10 2026-04-21 07:07:24 +00:00
  • ec2acec8a1 Harden LoRA checkpoint loading against untrusted pickle payloads JunghwanNA 2026-04-18 00:31:28 +09:00
  • 13605c5a0e Merge pull request #266 from linyueqian/docs/add-vllm-omni-references xliucs 2026-04-17 10:46:21 +08:00
  • afa63e6195 docs: add vLLM-Omni serving references Yueqian Lin 2026-04-16 21:19:27 -05:00
  • eae0a29908 docs: add ComfyUI RH link liuxin 2026-04-16 11:46:40 +08:00
  • 35895982d7 Merge PR #212: perf: stateful streaming VAE decode — eliminate redundant overlap Labmem-Zhouyx 2026-04-15 16:01:38 +08:00
  • f7f1b78c4d fix: correct transpose conv context Labmem-Zhouyx 2026-04-15 16:01:02 +08:00
  • 38d61cdf03 fix(mps): force float32 on Apple Silicon to avoid bf16 quality loss oumnya 2026-04-15 12:22:56 +08:00
  • 1565e83efe fix: complete shared generator cleanup coverage 刘鑫 2026-04-13 17:39:05 +08:00
  • 61b36d4e56 refactor: centralize generator cleanup in model helpers 刘鑫 2026-04-13 16:57:08 +08:00
  • b1584aec7c fix: stabilize CPU SDPA mask broadcasting 刘鑫 2026-04-13 15:38:53 +08:00
  • 4457617953 feat: add voxcpm validate CLI for pre-flight training data checks supermario_leo 2026-04-13 03:14:50 +08:00
  • 5510503182 Merge pull request #246 from sharziki/fix/unclosed-file-handles xliucs 2026-04-11 13:10:04 +08:00
  • fb46aad9a5 fix: close file handles in from_local() config loading sharziki 2026-04-11 00:01:14 -04:00
  • e4e049624c update finetuning pipeline and runtime device handling 刘鑫 2026-04-11 11:08:50 +08:00
  • abf01b9bf3 Merge pull request #229 from kuishou68/fix/issue-228-validate-text-type-order xliucs 2026-04-10 10:30:15 +08:00
  • 4f4a5b9f6c fix: correct type-check order in _generate() to prevent AttributeError on non-string input cocoon 2026-04-09 16:13:40 +00:00
  • 79c0cf68dd chore: remove accidentally committed app_local.py 刘鑫 2026-04-09 16:05:18 +08:00
  • 75cfa3e9b8 fix: use uncompiled feat_encoder for prefill to prevent CUDA Graph dynamic shape accumulation (#209) 刘鑫 2026-04-09 16:00:17 +08:00
  • 5611bd08a0 optim app.py Labmem-Zhouyx 2026-04-09 00:30:19 +08:00
  • 66205135fc perf: stateful streaming VAE decode — eliminate redundant overlap Kevin Knoedler 2026-04-08 09:06:13 -07:00
  • 364eff6840 update readme: python version Labmem-Zhouyx 2026-04-08 23:07:38 +08:00
  • 6d10932b09 update readme Labmem-Zhouyx 2026-04-08 18:48:58 +08:00
  • 68af4fe502 fix: ft log and setting 2.0.2 Labmem-Zhouyx 2026-04-08 18:15:17 +08:00
  • ee3649c1b3 fix: streaming decode Labmem-Zhouyx 2026-04-08 17:25:54 +08:00
  • 82d77d445c fix: decode chunksize for audiovae_v2 Labmem-Zhouyx 2026-04-08 16:31:36 +08:00
  • 8f95d13073 update readme: 30-language asr result on internal benchmark Labmem-Zhouyx 2026-04-08 15:36:56 +08:00
  • df38f0a167 update readme for modelscope download 2.0.1 Labmem-Zhouyx 2026-04-08 11:29:19 +08:00
  • 9adfaf6996 update demo for zh Labmem-Zhouyx 2026-04-08 00:15:16 +08:00
  • 46cfce0c97 fix VoxCPM2 training sample_rate: 48000 -> 16000 (match AudioVAE encoder) 刘鑫 2026-04-07 22:57:42 +08:00
  • da700f264e update ZH readme Labmem-Zhouyx 2026-04-07 18:04:56 +08:00
  • 9da570d409 remove wechat link Labmem-Zhouyx 2026-04-07 15:29:12 +08:00
  • 9374524c47 update readme Labmem-Zhouyx 2026-04-06 23:01:16 +08:00
  • ec6d30e996 update readme Labmem-Zhouyx 2026-04-06 22:56:06 +08:00
  • a010d621ff update readme 2.0.0 dev_2.0 Labmem-Zhouyx 2026-04-06 22:09:24 +08:00
  • 3f005b0dbd Enhance README formatting and community section for better visibility Dennis Huang 2026-04-06 19:50:29 +08:00
  • 039c6e9f92 update Labmem-Zhouyx 2026-04-06 17:15:10 +08:00
  • 5734ab36b6 Update README Dennis Huang 2026-04-06 16:24:12 +08:00
  • 746631c38d update Labmem-Zhouyx 2026-04-06 16:10:50 +08:00
  • 07b8b5c01f update readme Labmem-Zhouyx 2026-04-06 15:53:58 +08:00
  • f738cc9946 update Labmem-Zhouyx 2026-04-03 18:46:29 +08:00
  • 0c2cf23617 Update app.py UI, adjust streaming_prefix_len, remove legacy docs Labmem-Zhouyx 2026-04-03 18:42:41 +08:00
  • b823d8107c Merge branch 'dev_2.0' of https://github.com/OpenBMB/VoxCPM into dev_2.0 Labmem-Zhouyx 2026-04-03 17:44:46 +08:00
  • a87739426f add voxcpm2 finetune conf 刘鑫 2026-04-03 14:23:15 +08:00
  • 12c2b8ff98 update readme Labmem-Zhouyx 2026-04-02 21:01:23 +08:00
  • 30c300cfe8 adjust default cfg range 刘鑫 2026-04-02 18:14:35 +08:00
  • addee2c550 surport voxcpm2 cli 刘鑫 2026-04-01 21:15:55 +08:00
  • 42c428164c feat: add no_rope support for residual LM and fix streaming continuation decoding Labmem-Zhouyx 2026-03-31 17:07:33 +08:00
  • d9cf376e16 update voxcpm2 刘鑫 2026-03-31 11:50:37 +08:00
  • 23ed7ffeee fix: fix some bugs in resuming multi-GPU training 刘鑫 2026-03-13 18:43:07 +08:00
  • 7823e14b82 Merge pull request #188 from haosenwang1018/fix/bare-excepts xliucs 2026-03-03 11:49:00 +08:00
  • 8df79de636 fix: use specific exceptions instead of bare except haosenwang1018 2026-02-24 22:19:45 +00:00
  • acaadb19e9 Merge pull request #186 from symhsym/patch-1 xliucs 2026-02-11 18:05:39 +08:00
  • 07e526a231 Update train_voxcpm_finetune.py symhsym 2026-02-11 11:17:47 +08:00
  • 7aadc6c94e Merge pull request #161 from s3ldc/cli-arg-validation xliucs 2026-01-24 13:06:30 +08:00
  • 8f3a91cac8 cli: improve argument validation and help text for VoxCPM CLI Biriy 2026-01-20 14:33:58 +05:30
  • e72fb42c38 Merge pull request #147 from zanellig/main xliucs 2026-01-19 12:41:22 +08:00
  • 6dd63a534f fix: feature checkboxes Gonzalo Zanelli 2026-01-18 18:03:24 -03:00
  • 79e75f259e Fix: optimize save ckpt function 刘鑫 2026-01-16 16:22:34 +08:00
  • e8dd956fc2 Print all log messages to stderr instead of stdout 刘鑫 2026-01-12 15:30:45 +08:00
  • db75a7269b Merge pull request #141 from vytskalt/main xliucs 2026-01-12 15:06:51 +08:00
  • f2e203d5e2 print debug messages to stderr instead of stdout vytskalt 2026-01-09 20:05:52 +02:00
  • 6ecc00a5d3 Merge pull request #139 from lrjerryli/main xliucs 2026-01-04 16:08:09 +08:00
  • 8cfd9d155a Add torchcodec to dependencies 李睿杰JerryLi 2026-01-02 21:00:23 +08:00
  • 6499215204 Optimize logging validation set results to TensorBoard 刘鑫 2025-12-27 11:49:04 +08:00
  • d57ac634f8 Merge pull request #128 from jayll1303/feat/optimize-data-loader xliucs 2025-12-20 14:19:35 +08:00
  • de11c6a8cb OPTIMIZE: Improve sample length computation by using batch column access jayllfpt 2025-12-20 06:32:39 +07:00
  • ee5f2567ac FIX:When a prompt is present, concatenate two patches as the context for VAE decoding 刘鑫 2025-12-15 20:37:02 +08:00
  • b3a2d95fec FIX:When a prompt is present, concatenate two patches as the context for VAE decoding 刘鑫 2025-12-15 20:35:46 +08:00
  • aabda60833 add lora finetune data setting QA 刘鑫 2025-12-10 20:25:24 +08:00
  • a266c0a88d add lora funetine webUI; optimize lora save and load logic 刘鑫 2025-12-09 21:34:39 +08:00
  • 0779a93697 Merge branch 'main' of https://github.com/OpenBMB/VoxCPM Labmem-Zhouyx 2025-12-07 02:02:08 +08:00
  • a1f9d0c3b6 Update: release note Labmem-Zhouyx 2025-12-07 01:59:53 +08:00
  • aefba63f71 Merge pull request #98 from Ayin1412/main xliucs 2025-12-06 17:38:19 +08:00
  • 58717d7d82 修复lora/ft测试代码处传参错误的内容 Ayin1412 2025-12-06 14:49:35 +08:00
  • 1b0ff5693c Update: model parameters Labmem-Zhouyx 2025-12-06 01:22:30 +08:00
  • 762815a5b7 Update: user guides Labmem-Zhouyx 2025-12-05 23:57:43 +08:00
  • 5b13a35ea6 Update: gradio description Labmem-Zhouyx 2025-12-05 23:47:35 +08:00
  • 3ba727a615 Update: gradio description Labmem-Zhouyx 2025-12-05 23:38:04 +08:00
  • a7a447b02a Merge branch 'dev_1.5' 1.5.0 Labmem-Zhouyx 2025-12-05 22:38:03 +08:00
  • 81467f649f Modify lora inference api dev_1.5 刘鑫 2025-12-05 22:29:44 +08:00
  • 400f47a516 Modify lora inference api 刘鑫 2025-12-05 22:22:13 +08:00
  • b1f7593ae0 Update: default no denoise & normalize Labmem-Zhouyx 2025-12-05 22:16:27 +08:00
  • 6a5e713698 fix: streaming mode Labmem-Zhouyx 2025-12-05 22:06:15 +08:00
  • 3443dbb212 Update: VoxCPM1.5 and fine-tuning supprt Labmem-Zhouyx 2025-12-05 21:00:01 +08:00
  • 461ad7e506 Update: VoxCPM1.5 and fine-tuning supprt Labmem-Zhouyx 2025-12-05 21:00:01 +08:00
  • d1bb6aaf41 update technical report 1.0.5 Labmem-Zhouyx 2025-09-30 10:40:19 +08:00
  • 2eb4d39719 FX: Add MPS support 刘鑫 2025-09-28 21:06:35 +08:00