christian.schwarz/VibeVoice
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
86 Commits 3 Branches 0 Tags
4c419978c96877acee1f290921dbb5e40f577bbd
Commit Graph

86 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Zhiliang Peng 4c419978c9 Merge pull request #255 from sd983527/main 
Add news about VibeVoice ASR Transformers integration
 2026-03-06 14:08:47 +08:00
Yan Xia 7e73beec97 Add news about VibeVoice ASR Transformers integration 
- Added announcement that VibeVoice ASR is now part of Transformers v5.3.0 release
- Linked to the official Hugging Face Transformers release page
- Positioned as the latest news item with today's date

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-03-06 13:32:21 +08:00
Li Dong 7ef9dbe300 Merge pull request #247 from Damon-Salvetore/fix/vllm-version-compat 
fix: vllm-version-stable
 2026-02-28 11:12:24 +08:00
Damon-Salvetore 165e17e5ed fix: vllm-version-stable 2026-02-25 07:30:43 +00:00
Jianwei Yu 1807b858d4 Merge pull request #236 from Damon-Salvetore/main 
fix backend
 2026-02-10 00:07:05 +08:00
YingboHAO a4add8e52f fix backend 2026-02-08 09:58:19 +00:00
Jianwei Yu ce3d40c78f Merge pull request #233 from Damon-Salvetore/main 
Add hot words support
 2026-02-07 12:32:03 +08:00
YingboHAO 0508c3e86f fix 2026-02-06 14:38:16 +00:00
YingboHAO 7761242bf3 fix 2026-02-06 05:52:48 +00:00
YingboHAO bb54f78d0e feat: add hotwords support for vLLM ASR 2026-02-04 10:33:20 +00:00
YaoyaoChang 0aa8cb4c64 fx default speaker 2026-02-03 00:35:04 -08:00
YaoyaoChang e43c1e2cdb streaming use transformers==4.51.3 2026-02-03 00:30:52 -08:00
Jianwei Yu e16491d65e Merge pull request #228 from Damon-Salvetore/vllm-1 
[Fix] Resolve occasional infinite loops during vLLM inference
 2026-02-03 10:38:40 +08:00
YingboHAO e26f1c263f 1 2026-02-02 13:50:27 +00:00
YingboHAO 0055161273 Add test_api_auto_recover.py and test audio files 2026-02-02 13:49:01 +00:00
Zhiliang Peng b2aee8015c Delete docs/VibeVoice-ASR-Report.pdf 2026-01-28 19:33:37 +08:00
YaoyaoChang 2ee94fab1d update ASR architechture figure 2026-01-27 05:11:35 -08:00
YaoyaoChang 3140709188 update README 2026-01-27 21:06:31 +08:00
YaoyaoChang c435ae05d5 update README 
Added a section on LoRA fine-tuning to the ASR documentation.
 2026-01-27 21:01:40 +08:00
YaoyaoChang 0e1a0d39fd update README 2026-01-27 20:59:25 +08:00
YaoyaoChang 142a00112e update ASR README: multilingual 2026-01-27 20:58:10 +08:00
YaoyaoChang 4648c50ea0 update ASR Technical Report link to Arxiv 2026-01-27 12:58:06 +08:00
MLSDCherryPick cbbdb69474 add VibeVoice-ASR technique report arxiv link 2026-01-27 02:45:16 +00:00
YaoyaoChang a69e77c036 1. unify env for TTS and ASR; 2. avoid transformers 5.0.0 temporarily 2026-01-26 03:29:02 -08:00
YaoyaoChang a00f431e14 tts support latest transformers(4.57.6) 2026-01-26 03:28:10 -08:00
Jianwei Yu c4ee4fe716 Merge pull request #213 from Damon-Salvetore/vllm-1 
Replace install_deps.sh with start_server.py one-click deployment
 2026-01-26 16:49:38 +08:00
YingboHAO 1eb04f53a2 Replace install_deps.sh with start_server.py one-click deployment 2026-01-26 07:34:54 +00:00
ikeshav26 d11d756b61 fix: issues in error handling 2026-01-26 14:18:34 +08:00
YaoyaoChang 0926f242ce add CONTRIBUTING.md 2026-01-25 22:07:40 -08:00
DDXDB 1c5dbc4190 Add XPU sdpa Support 2026-01-26 14:00:31 +08:00
ThanhNguyxn 523713e806 fix(demo): add MPS and CPU support for ASR inference demo 
- Add MPS device choice and auto-detect MPS availability
- Change default attention implementation to 'auto' with smart fallback
- Auto-detect flash_attention_2 availability on CUDA, fallback to sdpa
- Use sdpa for MPS and CPU devices (flash_attention_2 not supported)
- Use float32 dtype for MPS/CPU devices for better compatibility

Fixes #206
 2026-01-26 13:56:11 +08:00
ThanhNguyxn 5cf026569e fix: handle torch.dtype serialization in config classes 
Fixes #199 - Object of type dtype is not JSON serializable

When loading models with torch_dtype as a torch.dtype object (e.g.,
torch.bfloat16), transformers would fail to serialize the config to
JSON for logging purposes, raising TypeError.

This fix:
- Adds _convert_dtype_to_string() helper function to convert torch.dtype
  objects to their string representation (e.g., 'bfloat16')
- Overrides to_dict() method in VibeVoiceConfig, VibeVoiceASRConfig,
  and VibeVoiceStreamingConfig to apply this conversion

The fix is backward compatible - string dtype values and None values
continue to work as expected.
 2026-01-26 13:45:55 +08:00
YaoyaoChang e67b15f47d update 2026-01-25 21:41:42 -08:00
MLSDCherryPick d9068541cf 1 2026-01-25 16:11:02 +00:00
YaoyaoChang c28e23f80c update language distribution figure 2026-01-25 00:15:11 -08:00
MLSDCherryPick 81bf8baa89 1 2026-01-25 05:14:39 +00:00
MLSDCherryPick e4036e46f4 1 2026-01-24 08:28:05 +00:00
Jianwei Yu 3c50e50d18 Merge pull request #203 from Damon-Salvetore/vibevoice-vllm 
Add vLLM plugin support for high-performance ASR serving
 2026-01-24 16:17:10 +08:00
MLSDCherryPick 71356b87dd Language support 2026-01-24 05:17:26 +00:00
MLSDCherryPick 7d12252de3 Language support 2026-01-24 05:11:34 +00:00
MLSDCherryPick a3e99daedd Language support 2026-01-24 05:10:47 +00:00
YingboHAO 04f8bc40b0 Update test_api.py 2026-01-23 17:47:31 +00:00
YingboHAO 4df5b0582f Add vLLM plugin support for high-performance ASR serving 2026-01-23 17:32:24 +00:00
YaoyaoChang c0c2af984e update README for finetuning-asr 2026-01-22 06:20:11 -08:00
Zhiliang Peng 05e1a022e5 Update FT README 
Clarified the purpose of the toy dataset in the README.
 2026-01-22 21:49:47 +08:00
Zhiliang Peng 59c90e7633 Merge pull request #197 from pengzhiliang/vibevoice_asr_ft 
add VibeVoice-ASR finetuning code
 2026-01-22 21:45:35 +08:00
pengzhiliang 8516386ce4 update ft readme 2026-01-22 05:44:34 -08:00
pengzhiliang cef628e1b5 update ft code 2026-01-22 05:20:25 -08:00
pengzhiliang db2f1d9ff3 init vibevoice-asr ft 2026-01-22 05:04:33 -08:00
YaoyaoChang 875115c000 update README 2026-01-22 01:28:21 -08:00