Hugging Face's logo

mudler
/
vibevoice.cpp-models

GGUF
VibeVoice
vibevoice.cpp
tts
asr
speech
ggml
Model card Files
xet
 Community
1
lokegud commited on
Commit
a72a041
·
verified ·
1 Parent(s): a67807e

Add 23 pre-converted voice GGUFs (DE/EN/FR/IN/IT/JP/KR/NL/PL/PT/SP)

Browse files

Adds the 23 voice GGUFs not currently in this repo, pre-converted from the upstream Microsoft VibeVoice demo voices in `microsoft/VibeVoice/demo/voices/streaming_model/`.

Repo previously had: `voice-en-Carter_man.gguf`, `voice-en-Emma.gguf`. After this PR, all 25 voices ship pre-converted - anyone using vibevoice.cpp can `hf download mudler/vibevoice.cpp-models --local-dir models` and have every voice ready, no torch install or conversion script run required.

### Voices added
- **EN (4)**: Davis (m), Frank (m), Grace (w), Mike (m)
- **DE**: Spk0 (m), Spk1 (w)
- **FR**: Spk0 (m), Spk1 (w)
- **IT**: Spk0 (w), Spk1 (m)
- **SP**: Spk0 (w), Spk1 (m)
- **PT**: Spk0 (w), Spk1 (m)
- **NL**: Spk0 (m), Spk1 (w)
- **PL**: Spk0 (m), Spk1 (w)
- **JP**: Spk0 (m), Spk1 (w)
- **KR**: Spk0 (w), Spk1 (m)
- **IN**: Samuel (m)

Total ~176 MB across 23 files.

### Conversion details
- Script: `scripts/convert_voice_to_gguf.py` from `mudler/vibevoice.cpp` (this repo's tooling project)
- Source: `https://github.com/microsoft/VibeVoice/raw/main/demo/voices/streaming_model/<name>.pt`
- Smoke-tested four (PL-Spk1, FR-Spk1, JP-Spk1, IN-Samuel) end-to-end with English text + the realtime-0.5B-q8_0 model - all produce valid 24kHz mono PCM WAVs. Foreign-language voices speak English with their native accent (as expected - the voice GGUF carries timbre/prosody, the model handles language).

### Naming convention
Kept upstream's `<lang>-<name>_<gender>.pt` -> `voice-<lang>-<name>_<gender>.gguf`. Note the existing `voice-en-Emma.gguf` in this repo dropped the `_woman` suffix; if you'd like all files normalized one way (with or without gender suffix), happy to follow up.

### Licensing
Voices are part of the official Microsoft VibeVoice demo distribution (MIT). Conversion tooling here is MIT. Conversion is straightforward derivative work; no new license obligations introduced.

Files changed (24) hide show
  1. .gitattributes +23 -0
  2. voice-de-Spk0_man.gguf +3 -0
  3. voice-de-Spk1_woman.gguf +3 -0
  4. voice-en-Davis_man.gguf +3 -0
  5. voice-en-Frank_man.gguf +3 -0
  6. voice-en-Grace_woman.gguf +3 -0
  7. voice-en-Mike_man.gguf +3 -0
  8. voice-fr-Spk0_man.gguf +3 -0
  9. voice-fr-Spk1_woman.gguf +3 -0
  10. voice-in-Samuel_man.gguf +3 -0
  11. voice-it-Spk0_woman.gguf +3 -0
  12. voice-it-Spk1_man.gguf +3 -0
  13. voice-jp-Spk0_man.gguf +3 -0
  14. voice-jp-Spk1_woman.gguf +3 -0
  15. voice-kr-Spk0_woman.gguf +3 -0
  16. voice-kr-Spk1_man.gguf +3 -0
  17. voice-nl-Spk0_man.gguf +3 -0
  18. voice-nl-Spk1_woman.gguf +3 -0
  19. voice-pl-Spk0_man.gguf +3 -0
  20. voice-pl-Spk1_woman.gguf +3 -0
  21. voice-pt-Spk0_woman.gguf +3 -0
  22. voice-pt-Spk1_man.gguf +3 -0
  23. voice-sp-Spk0_woman.gguf +3 -0
  24. voice-sp-Spk1_man.gguf +3 -0
.gitattributes CHANGED
@@ -39,3 +39,26 @@ voice-en-Carter_man.gguf filter=lfs diff=lfs merge=lfs -text
39
  vibevoice-realtime-0.5B-q8_0.gguf filter=lfs diff=lfs merge=lfs -text
40
  vibevoice-asr-q8_0.gguf filter=lfs diff=lfs merge=lfs -text
41
  vibevoice-asr-q4_k.gguf filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
39
  vibevoice-realtime-0.5B-q8_0.gguf filter=lfs diff=lfs merge=lfs -text
40
  vibevoice-asr-q8_0.gguf filter=lfs diff=lfs merge=lfs -text
41
  vibevoice-asr-q4_k.gguf filter=lfs diff=lfs merge=lfs -text
42
+ voice-de-Spk0_man.gguf filter=lfs diff=lfs merge=lfs -text
43
+ voice-de-Spk1_woman.gguf filter=lfs diff=lfs merge=lfs -text
44
+ voice-en-Davis_man.gguf filter=lfs diff=lfs merge=lfs -text
45
+ voice-en-Frank_man.gguf filter=lfs diff=lfs merge=lfs -text
46
+ voice-en-Grace_woman.gguf filter=lfs diff=lfs merge=lfs -text
47
+ voice-en-Mike_man.gguf filter=lfs diff=lfs merge=lfs -text
48
+ voice-fr-Spk0_man.gguf filter=lfs diff=lfs merge=lfs -text
49
+ voice-fr-Spk1_woman.gguf filter=lfs diff=lfs merge=lfs -text
50
+ voice-in-Samuel_man.gguf filter=lfs diff=lfs merge=lfs -text
51
+ voice-it-Spk0_woman.gguf filter=lfs diff=lfs merge=lfs -text
52
+ voice-it-Spk1_man.gguf filter=lfs diff=lfs merge=lfs -text
53
+ voice-jp-Spk0_man.gguf filter=lfs diff=lfs merge=lfs -text
54
+ voice-jp-Spk1_woman.gguf filter=lfs diff=lfs merge=lfs -text
55
+ voice-kr-Spk0_woman.gguf filter=lfs diff=lfs merge=lfs -text
56
+ voice-kr-Spk1_man.gguf filter=lfs diff=lfs merge=lfs -text
57
+ voice-nl-Spk0_man.gguf filter=lfs diff=lfs merge=lfs -text
58
+ voice-nl-Spk1_woman.gguf filter=lfs diff=lfs merge=lfs -text
59
+ voice-pl-Spk0_man.gguf filter=lfs diff=lfs merge=lfs -text
60
+ voice-pl-Spk1_woman.gguf filter=lfs diff=lfs merge=lfs -text
61
+ voice-pt-Spk0_woman.gguf filter=lfs diff=lfs merge=lfs -text
62
+ voice-pt-Spk1_man.gguf filter=lfs diff=lfs merge=lfs -text
63
+ voice-sp-Spk0_woman.gguf filter=lfs diff=lfs merge=lfs -text
64
+ voice-sp-Spk1_man.gguf filter=lfs diff=lfs merge=lfs -text
voice-de-Spk0_man.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94f542e334905ba06d6f1eb5e225f58195f5c02c0acf219681cafa1e9587203f
3
+ size 14024064
voice-de-Spk1_woman.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2822dc578b75ab2c8c562b35662c01cfc5c740f94413549c559ee75937e9d04b
3
+ size 10526080
voice-en-Davis_man.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f396a159dd3fa08ab1eff23a8591d5ed6e5946a87a745585f3b02a5dc5c8f6fa
3
+ size 4903296
voice-en-Frank_man.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5856937d9e32c71715fd86362e2cab3acd14b2c82034c75e5c4d1542e9c7700e
3
+ size 6679936
voice-en-Grace_woman.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93f2a254ad2835f669875298104a903e76eec7eb9c1e6cb90ede23053e382afb
3
+ size 5505920
voice-en-Mike_man.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86754e97fbaefea6c828990f5d39ffcd2a66106145601bdf562ab23faac763b7
3
+ size 3976576
voice-fr-Spk0_man.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f99ba32d406601f0f2083b30034bd1c1790f81c64888c8ba40b3fc7151194d0
3
+ size 8717696
voice-fr-Spk1_woman.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:066e03d1ac109f2135afbd7f4f93b58f6440cf82b0196df5d33eb6fb2f6c7029
3
+ size 8488320
voice-in-Samuel_man.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:989057bdde8f6306e45d4f0f4e6f0e62b9f9c924dca6270b809e064f74f9242c
3
+ size 7525760
voice-it-Spk0_woman.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47c477998dfd49a91c8716b7b2ec895b92ba77a3976f69a70747ef3e8fe03f2c
3
+ size 5048704
voice-it-Spk1_man.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d792b6f8ebca190068e31e7338a060d715b4219721bf26734dbd64075b0752b
3
+ size 5653888
voice-jp-Spk0_man.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f5803efe705596c86891f27bd6a50ac148a2aeb2ff8ffe24e368ffb247f006f
3
+ size 9281408
voice-jp-Spk1_woman.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f539803730298c0e4460cf61a40debf31ee6685cb9b5916ac8c145d50f8a0810
3
+ size 9219968
voice-kr-Spk0_woman.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad49a73db180c7df4c569802f2dd3c8a0a24882b4485f65a1237116b17c087e6
3
+ size 8251776
voice-kr-Spk1_man.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99a9c058132e60301168015c59b00f37fdac719d4f74697c24f93bc7cfeeb069
3
+ size 11675008
voice-nl-Spk0_man.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45aab8c8f851e0f84029d12b48917f3dadfc05af46953ed27fd3b43ee48ae563
3
+ size 7353728
voice-nl-Spk1_woman.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2bfd30241630379ce465f8c2d55a705a069304ffb4c48a811c4271b03efb2cca
3
+ size 10135936
voice-pl-Spk0_man.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37ef0a5bbe8eee468dec0ba588931b1f8e7f9b82704b5769209b249a0dd27328
3
+ size 7446400
voice-pl-Spk1_woman.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d2a57f5afbdadc984d940185d8381a6aada855a6a9bf954a4a99b880f7ff5c8
3
+ size 9901440
voice-pt-Spk0_woman.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:daeb7d037d3eb6069aa9b4345fe38c0a0b22678d44e6d5920fa99a0aaf11c712
3
+ size 4480896
voice-pt-Spk1_man.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b63bcc762cd46094ba1f74c5f189e7aa4b9fd41bdcacc2bd128ee67f29f3658
3
+ size 7054720
voice-sp-Spk0_woman.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0947c31154387834a4e7c37a24c21fbf7d52bb20958c7af611f3e78cf4a6f9d
3
+ size 8432000
voice-sp-Spk1_man.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:386dfaa61ede30226fdfc85480f9d2608b298f8a8d655af68c450afbec201f8d
3
+ size 10205568