Upload folder using huggingface_hub

.gitattributes

@@ -33,8 +33,9 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
-Higgs-Audio-v3-STT-GGUF/higgs-audio-v3-stt-f16.gguf filter=lfs diff=lfs merge=lfs -text
-Higgs-Audio-v3-STT-GGUF/higgs-audio-v3-stt-q8_0.gguf filter=lfs diff=lfs merge=lfs -text
-Sortformer-Diar-4spk-v1-GGUF/sortformer-diar-4spk-v1-f16.gguf filter=lfs diff=lfs merge=lfs -text
-Sortformer-Diar-4spk-v1-GGUF/sortformer-diar-4spk-v1-q8_0.gguf filter=lfs diff=lfs merge=lfs -text
-VibeVoice-1.5B-GGUF/vibevoice-1.5b-q4-ios.gguf filter=lfs diff=lfs merge=lfs -text
+Irodori-TTS-500M-v3-GGUF/irodori-tts-500m-v3-f16.gguf filter=lfs diff=lfs merge=lfs -text
+Irodori-TTS-500M-v3-GGUF/irodori-tts-500m-v3-q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+Irodori-TTS-600M-v3-VoiceDesign-GGUF/irodori-tts-600m-v3-voicedesign-f16.gguf filter=lfs diff=lfs merge=lfs -text
+Irodori-TTS-600M-v3-VoiceDesign-GGUF/irodori-tts-600m-v3-voicedesign-q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+Irodori-TTS-v4-Small-GGUF/irodori-tts-v4-small-f16.gguf filter=lfs diff=lfs merge=lfs -text
+Irodori-TTS-v4-Small-GGUF/irodori-tts-v4-small-q8_0.gguf filter=lfs diff=lfs merge=lfs -text

Irodori-TTS-500M-v3-GGUF/irodori-tts-500m-v3-f16.gguf

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc58da653f5db990c31bf5e09fd50460042a1af27c195f5229194a73fa308318
-size 1254805632
+oid sha256:24c5d7224c056dd9464c30214067369b0b6e8cb28646e6eda3f41bd8bad332b7
+size 1254813120

Irodori-TTS-500M-v3-GGUF/irodori-tts-500m-v3-q8_0.gguf

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f1d8d84f92207d4da674c9f6d350c692b7fde7c1fbaff4e7067fe7023b4b0c4
-size 1093732096
+oid sha256:4849d69925732232c3f72dedb5d5ae18808b1ca93f5709575829bfbca32a036f
+size 1093739584

Irodori-TTS-600M-v3-VoiceDesign-GGUF/irodori-tts-600m-v3-voicedesign-f16.gguf

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7a1b999f6b3abe670c51b6728485d4bfa8fa2ff5055bc5ddf38f8bee94b5568
-size 1463780160
+oid sha256:0c40eb114abd94a26270c43f0498c2295df510beab366bc4a5345f1b50820b8c
+size 1463787680

Irodori-TTS-600M-v3-VoiceDesign-GGUF/irodori-tts-600m-v3-voicedesign-q8_0.gguf

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eda37824d020f90a5f7bf831cee8145714b35b93876651765fc516637f425b33
-size 1272132576
+oid sha256:9f8c305fcf9a79d9afc1bdd9b030934822f6d66e58e93ad92553e712ceb057b5
+size 1272140064

Irodori-TTS-v4-Small-GGUF/irodori-tts-v4-small-f16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7a55b28287999f0094db9f1093d4b035c2d60a36cb9db86eed743bcebb72d20
+size 1762161536

Irodori-TTS-v4-Small-GGUF/irodori-tts-v4-small-q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2a0daf22851e1c8a38617e34e89f67d2508ccff871a871fc66372e34bbe66d9
+size 1369004544

README.md

@@ -20,10 +20,12 @@ base_model:
 - ACE-Step/acestep-v15-base
 - Aratako/Irodori-TTS-500M-v3
 - Aratako/Irodori-TTS-600M-v3-VoiceDesign
+- Aratako/Irodori-TTS-v4-Small
 - Aratako/MioCodec-25Hz-44.1kHz-v2
 - Aratako/MioTTS-1.7B
 - Aratako/Semantic-DACVAE-Japanese-32dim
 - Banafo/Kroko-ASR
+- dots-studio/dots.tts-mf
 - dots-studio/dots.tts-soar
 - fishaudio/s2-pro
 - FunAudioLLM/Fun-ASR-Nano-2512-hf
@@ -60,6 +62,7 @@ base_model:
 - mlx-community/wavlm-base-plus-mlx
 - syvai/hviske-v5.3
 - nvidia/diar_sortformer_4spk-v1
+- nvidia/magpie_tts_multilingual_357m
 - nvidia/nemotron-3.5-asr-streaming-0.6b
 - nvidia/parakeet-tdt-0.6b-v3
 - owensong/Inflect-Micro-v2
@@ -86,49 +89,52 @@ for the full matrix and drift notes.
 
 | Directory | Files | audio.cpp family | Tested | Original model license |
 |---|---|---|---|---|
-| `ACE-Step1.5-GGUF` | `base/ace-step-1.5-base-bf16.gguf`, `base/ace-step-1.5-base-q8_0.gguf`, `turbo/ace-step-1.5-turbo-bf16.gguf`, `turbo/ace-step-1.5-turbo-q8_0.gguf` | `ace_step` | 16-bit + Q8 drift | See original model package |
-| `BS-RoFormer-ep368-GGUF` | `bs-roformer-ep368-q8_0.gguf` | `bs_roformer` | Q8 pass | See original model package |
+| `ACE-Step1.5-GGUF` | `base/ace-step-1.5-base-bf16.gguf`, `base/ace-step-1.5-base-q8_0.gguf`, `turbo/ace-step-1.5-turbo-bf16.gguf`, `turbo/ace-step-1.5-turbo-q8_0.gguf` | `ace_step` | 16-bit + Q8 drift | MIT |
+| `BS-RoFormer-ep368-GGUF` | `bs-roformer-ep368-q8_0.gguf` | `bs_roformer` | Q8 pass | Apache-2.0 |
 | `Chatterbox-GGUF` | `chatterbox-f16.gguf`, `chatterbox-q8_0.gguf` | `chatterbox` | 16-bit + Q8 ASR-match drift | MIT |
 | `Citrinet-ASR-GGUF` | `citrinet-asr-q8_0.gguf` | `citrinet_asr` | Q8 pass | CC-BY-4.0 |
-| `Confucius4-TTS-GGUF` | `confucius4-tts-orig.gguf` | `confucius4_tts` | orig pass | See original model package |
-| `DotTTS-SOAR-GGUF` | `dots-tts-soar-orig.gguf`, `dots-tts-soar-bf16.gguf` | `dots_tts` | experimental | See original model package |
-| `DramaBox-GGUF` | `dramabox-q8_0.gguf` | `dramabox` | Q8 pass | See original model package |
-| `Fish-Audio-S2-Pro-GGUF` | `fish-audio-s2-pro-bf16.gguf`, `fish-audio-s2-pro-q8_0.gguf` | `fish_audio` | 16-bit + Q8 pass | See original model package |
+| `Confucius4-TTS-GGUF` | `confucius4-tts-orig.gguf` | `confucius4_tts` | orig pass | Apache-2.0 |
+| `DotTTS-MF-GGUF` | `dots-tts-mf-bf16.gguf` | `dots_tts` | experimental | Apache-2.0 |
+| `DotTTS-SOAR-GGUF` | `dots-tts-soar-orig.gguf`, `dots-tts-soar-bf16.gguf` | `dots_tts` | experimental | Apache-2.0 |
+| `DramaBox-GGUF` | `dramabox-q8_0.gguf` | `dramabox` | Q8 pass | LTX-2 Community License |
+| `Fish-Audio-S2-Pro-GGUF` | `fish-audio-s2-pro-bf16.gguf`, `fish-audio-s2-pro-q8_0.gguf` | `fish_audio` | 16-bit + Q8 pass | Fish Audio Research License |
 | `Fun-ASR-Nano-2512-GGUF` | `fun-asr-nano-2512-f16.gguf`, `fun-asr-nano-2512-q8_0.gguf` | `fun_asr_nano` | 16-bit + Q8 pass | FunASR Model Open Source License Agreement v1.1 |
 | `HeartMuLa-GGUF` | `heartmula-f16.gguf`, `heartmula-q8_0.gguf` | `heartmula` | 16-bit + Q8 drift | Apache-2.0 |
-| `HTDemucs-GGUF` | `htdemucs-f16.gguf`, `htdemucs-q8_0.gguf` | `htdemucs` | 16-bit pass, Q8 drift | See original model package |
+| `HTDemucs-GGUF` | `htdemucs-f16.gguf`, `htdemucs-q8_0.gguf` | `htdemucs` | 16-bit pass, Q8 drift | MIT |
 | `Higgs-Audio-v3-STT-GGUF` | `higgs-audio-v3-stt-f16.gguf`, `higgs-audio-v3-stt-q8_0.gguf` | `higgs_audio_stt` | 16-bit + Q8 pass | Apache-2.0 |
-| `Higgs-Audio-v3-TTS-4B-GGUF` | `higgs-audio-v3-tts-4b-bf16.gguf`, `higgs-audio-v3-tts-4b-q8_0.gguf` | `higgs_audio_tts` | 16-bit + Q8 pass | See original model package |
-| `Hviske-v5.3-GGUF` | `hviske-v5.3-q8_0.gguf` | `hviske_asr` | Q8 pass | See original model package |
+| `Higgs-Audio-v3-TTS-4B-GGUF` | `higgs-audio-v3-tts-4b-bf16.gguf`, `higgs-audio-v3-tts-4b-q8_0.gguf` | `higgs_audio_tts` | 16-bit + Q8 pass | Boson Higgs TTS 3 Research and Non-Commercial License |
+| `Hviske-v5.3-GGUF` | `hviske-v5.3-q8_0.gguf` | `hviske_asr` | Q8 pass | CC-BY-NC-4.0 |
 | `IndexTTS2-GGUF` | `index-tts2-orig.gguf`, `index-tts2-f16.gguf`, `index-tts2-q8_0.gguf` | `index_tts2` | orig + 16-bit pass/drift, Q8 ASR-match drift | bilibili Model Use License Agreement |
-| `Inflect-Micro-v2-GGUF` | `inflect-micro-v2-orig.gguf` | `inflect_v2` | orig pass | See original model package |
+| `Inflect-Micro-v2-GGUF` | `inflect-micro-v2-orig.gguf` | `inflect_v2` | orig pass | Apache-2.0 |
 | `Irodori-TTS-500M-v3-GGUF` | `irodori-tts-500m-v3-f16.gguf`, `irodori-tts-500m-v3-q8_0.gguf` | `irodori_tts` | 16-bit pass, Q8 drift | MIT |
 | `Irodori-TTS-600M-v3-VoiceDesign-GGUF` | `irodori-tts-600m-v3-voicedesign-f16.gguf`, `irodori-tts-600m-v3-voicedesign-q8_0.gguf` | `irodori_tts` | 16-bit pass, Q8 drift | MIT |
-| `Kroko-ASR-GGUF` | `kroko-en-community-64-l-q8_0.gguf` | `kroko_asr` | Q8 pass | See original model package |
+| `Irodori-TTS-v4-Small-GGUF` | `irodori-tts-v4-small-f16.gguf`, `irodori-tts-v4-small-q8_0.gguf` | `irodori_tts` | 16-bit + Q8 pass | MIT |
+| `Kroko-ASR-GGUF` | `kroko-en-community-64-l-q8_0.gguf` | `kroko_asr` | Q8 pass | CC-BY-SA community model license |
 | `MOSS-TTS-Local-v1.5-GGUF` | `moss-tts-local-v1.5-bf16.gguf`, `moss-tts-local-v1.5-q8_0.gguf` | `moss_tts_local` | 16-bit pass, Q8 ASR-match drift | Apache-2.0 |
 | `MOSS-TTS-Nano-100M-GGUF` | `moss-tts-nano-100m-bf16.gguf`, `moss-tts-nano-100m-q8_0.gguf` | `moss_tts_nano` | 16-bit pass, Q8 ASR-match drift | Apache-2.0 |
+| `MagpieTTS-Multilingual-357M-GGUF` | `magpie-tts-multilingual-357m-orig.gguf` | `magpie_tts` | experimental | NVIDIA Open Model License |
 | `Mel-Band-RoFormer-GGUF` | `mel-band-roformer-f16.gguf`, `mel-band-roformer-q8_0.gguf` | `mel_band_roformer` | 16-bit + Q8 drift | MIT |
 | `MioCodec-25Hz-44.1kHz-v2-GGUF` | `miocodec-25hz-44khz-v2-orig.gguf`, `miocodec-25hz-44khz-v2-f16.gguf`, `miocodec-25hz-44khz-v2-q8_0.gguf` | `miocodec` | orig pass, 16-bit + Q8 drift | MIT |
 | `MioTTS-1.7B-GGUF` | `miotts-1.7b-orig.gguf`, `miotts-1.7b-bf16.gguf`, `miotts-1.7b-q8_0.gguf` | `miotts` | orig pass, 16-bit drift, Q8 ASR-match drift | Apache-2.0 |
 | `Nemotron-3.5-ASR-Streaming-0.6B-GGUF` | `nemotron-3.5-asr-streaming-0.6b-f16.gguf`, `nemotron-3.5-asr-streaming-0.6b-q8_0.gguf` | `nemotron_asr` | 16-bit pass, Q8 minor filler drift | OpenMDW-1.1 |
 | `OmniVoice-GGUF` | `omnivoice-bf16.gguf`, `omnivoice-f16.gguf`, `omnivoice-q8_0.gguf` | `omnivoice` | 16-bit + Q8 drift | Apache-2.0 |
-| `Parakeet-TDT-0.6B-v3-GGUF` | `parakeet-tdt-0.6b-v3-f16.gguf`, `parakeet-tdt-0.6b-v3-q8_0.gguf` | `parakeet_tdt` | 16-bit + Q8 pass | See original model package |
-| `PocketTTS-GGUF` | `english/`, `german/`, `italian/`, `portuguese/`, `spanish/` each contain `bf16` and `q8_0` GGUFs | `pocket_tts` | 16-bit pass, Q8 drift | See original model package |
+| `Parakeet-TDT-0.6B-v3-GGUF` | `parakeet-tdt-0.6b-v3-f16.gguf`, `parakeet-tdt-0.6b-v3-q8_0.gguf` | `parakeet_tdt` | 16-bit + Q8 pass | CC-BY-4.0 |
+| `PocketTTS-GGUF` | `english/`, `german/`, `italian/`, `portuguese/`, `spanish/` each contain `bf16` and `q8_0` GGUFs | `pocket_tts` | 16-bit pass, Q8 drift | CC-BY-4.0 |
 | `Qwen3-ASR-0.6B-GGUF` | `qwen3-asr-0.6b-f16.gguf`, `qwen3-asr-0.6b-q8_0.gguf` | `qwen3_asr` | 16-bit + Q8 pass | Apache-2.0 |
 | `Qwen3-ASR-1.7B-GGUF` | `qwen3-asr-1.7b-f16.gguf`, `qwen3-asr-1.7b-q8_0.gguf` | `qwen3_asr` | 16-bit + Q8 pass | Apache-2.0 |
 | `Qwen3-ForcedAligner-0.6B-GGUF` | `qwen3-forced-aligner-0.6b-f16.gguf`, `qwen3-forced-aligner-0.6b-q8_0.gguf` | `qwen3_forced_aligner` | 16-bit + Q8 pass | Apache-2.0 |
 | `Qwen3-TTS-12Hz-1.7B-Base-GGUF` | `qwen3-tts-12hz-1.7b-base-orig.gguf`, `qwen3-tts-12hz-1.7b-base-bf16.gguf`, `qwen3-tts-12hz-1.7b-base-q8_0_v2.gguf` | `qwen3_tts` | orig pass, 16-bit + Q8 ASR-match drift | Apache-2.0 |
 | `Qwen3-TTS-12Hz-1.7B-CustomVoice-GGUF` | `qwen3-tts-12hz-1.7b-customvoice-bf16.gguf`, `qwen3-tts-12hz-1.7b-customvoice-q8_0.gguf` | `qwen3_tts` | 16-bit + Q8 ASR-match drift | Apache-2.0 |
 | `Qwen3-TTS-12Hz-1.7B-VoiceDesign-GGUF` | `qwen3-tts-12hz-1.7b-voicedesign-bf16.gguf`, `qwen3-tts-12hz-1.7b-voicedesign-q8_0.gguf` | `qwen3_tts` | 16-bit + Q8 ASR-match drift | Apache-2.0 |
-| `RVC-GGUF` | `rvc-f16.gguf` | `rvc` | F16 pass | See original model package |
+| `RVC-GGUF` | `rvc-f16.gguf` | `rvc` | F16 pass | MIT |
 | `SeedVC-MLX-GGUF` | `seed-vc-mlx-orig.gguf`, `seed-vc-mlx-f16.gguf`, `seed-vc-mlx-q8_0.gguf` | `seed_vc` | 16-bit + Q8 drift | GPL-3.0 |
 | `Sortformer-Diar-4spk-v1-GGUF` | `sortformer-diar-4spk-v1-f16.gguf`, `sortformer-diar-4spk-v1-q8_0.gguf` | `sortformer_diar` | 16-bit + Q8 pass | CC-BY-NC-4.0 |
 | `Stable-Audio-3-Medium-GGUF` | `stable-audio-3-medium-f16.gguf`, `stable-audio-3-medium-q8_0.gguf` | `stable_audio` | 16-bit + Q8 drift | Stability AI Community License |
 | `Stable-Audio-3-Small-Music-GGUF` | `stable-audio-3-small-music-f16.gguf`, `stable-audio-3-small-music-q8_0.gguf` | `stable_audio` | 16-bit + Q8 drift | Stability AI Community License |
 | `Stable-Audio-3-Small-SFX-GGUF` | `stable-audio-3-small-sfx-f16.gguf`, `stable-audio-3-small-sfx-q8_0.gguf` | `stable_audio` | 16-bit + Q8 drift | Stability AI Community License |
 | `Supertonic-3-GGUF` | `supertonic-3-orig.gguf`, `supertonic-3-f16.gguf`, `supertonic-3-q8_0.gguf` | `supertonic` | F32/orig pass; f16 not tested; Q8 unsupported dtype | BigScience Open RAIL-M |
-| `Vevo2-GGUF` | `vevo2-orig.gguf`, `vevo2-f16.gguf`, `vevo2-q8_0.gguf` | `vevo2` | orig + 16-bit pass/drift; Q8 mixed route drift | See original model package |
-| `VibeVoice-1.5B-GGUF` | `vibevoice-1.5b-bf16.gguf`, `vibevoice-1.5b-q8_0.gguf` | `vibevoice` | 16-bit pass, Q8 drift | MIT |
+| `Vevo2-GGUF` | `vevo2-orig.gguf`, `vevo2-f16.gguf`, `vevo2-q8_0.gguf` | `vevo2` | orig + 16-bit pass/drift; Q8 mixed route drift | CC-BY-NC-ND-4.0 |
+| `VibeVoice-1.5B-GGUF` | `vibevoice-1.5b-bf16.gguf`, `vibevoice-1.5b-q8_0.gguf`, `vibevoice-1.5b-q4-ios.gguf` | `vibevoice` | 16-bit pass, Q8 drift | MIT |
 | `VibeVoice-ASR-GGUF` | `vibevoice-asr-f16.gguf`, `vibevoice-asr-q8_0.gguf` | `vibevoice_asr` | 16-bit + Q8 pass | MIT |
 | `VoxCPM2-GGUF` | `voxcpm2-orig.gguf`, `voxcpm2-bf16.gguf`, `voxcpm2-q8_0.gguf` | `voxcpm2` | orig pass, 16-bit + Q8 ASR-match drift | Apache-2.0 |
 | `Voxtral-Mini-4B-Realtime-2602-GGUF` | `voxtral-mini-4b-realtime-2602-bf16.gguf`, `voxtral-mini-4b-realtime-2602-q8_0.gguf`, `voxtral-mini-4b-realtime-2602-q4_k.gguf` | `voxtral_realtime` | 16-bit + Q8 pass; Q4_K quick check passed | Apache-2.0 |