Models
Datasets
Spaces
Buckets
Docs
Enterprise
Pricing
- Website
- Community
- Solutions
Log In
Sign Up

Collections

Discover the best community collections!

Collections trending this week

TTS — Voice-Clone Training Targets

Packaged non-raw reference/target pair shards for public voice-clone training.

instinct-org/audiobook_chunked_speech_restorised_tts_train_clone_pairs

Updated May 21 • 14
instinct-org/default_voices_chunked_speech_restorised_tts_train_clone_pairs

Updated May 21 • 13
instinct-org/espeech_podcasts_chunked_speech_restorised_tts_train_clone_pairs

Updated May 21 • 14
instinct-org/miscellaneous_yt_chunked_speech_restorised_tts_train_clone_pairs

Updated May 21 • 26

STT — Aligned Upstream Candidates

Restored or aligned STT repositories that are not in the validated 14-repository upstream set.

instinct-org/espeech_podcasts_chunked_nfa_aligned

Viewer • Updated May 21 • 231k • 19
instinct-org/espeech_podcasts_chunked_speech_restorised

Viewer • Updated May 21 • 2.48M • 47
instinct-org/miscellaneous_yt_chunked_speech_restorised

Viewer • Updated May 19 • 530k • 52
instinct-org/miscellaneous_yt_chunked_speech_restorised_nfa_aligned

Viewer • Updated May 26 • 528k • 21

Speech Sources — Unchunked

Long-form or minimally processed source speech datasets.

instinct-org/audio_youtube_unchunked

Viewer • Updated May 19 • 9.88k • 26
instinct-org/audiobook_unchunked

Viewer • Updated May 19 • 1.29M • 17
instinct-org/default_voices_unchunked

Viewer • Updated May 19 • 2.88k • 16
instinct-org/educational_unchunked

Viewer • Updated May 19 • 8.3k • 66

hai-hu/zh-pythia-2.8B

Updated Apr 3
hai-hu/zh-pythia-1.4B

Updated Apr 17
hai-hu/zh-pythia-1B

Updated May 26
hai-hu/zh-pythia-410M

Updated May 19

Running on Zero

Agents

Featured

1.19k

FLUX.2 [dev]

💻

1.19k

Generate or edit images from text and optional photos

Speech Sources — Segmented and Chunked

Reusable segmented or chunked speech datasets.

instinct-org/audio_youtube_chunked

Viewer • Updated May 19 • 560k • 59
instinct-org/audiobook_chunked

Viewer • Updated May 19 • 1.29M • 14
instinct-org/cv_chunked

Viewer • Updated Aug 16 • 71.2k • 15
instinct-org/default_voices_chunked

Viewer • Updated May 19 • 134k • 12

STT — Other Candidates

STT-oriented repositories awaiting full lineage and release validation.

instinct-org/pods

Viewer • Updated Jun 6 • 263 • 13
instinct-org/stt_dataset_uzbek

Viewer • Updated May 19 • 907 • 15
instinct-org/uf_hd

Viewer • Updated Jun 8 • 2.25k • 19

HuggingFaceCode/stack-v3-full

52.8 TB

This Model Safetensors and GGUF: 10 Models

Running

Agents

145

Omni-image-editor-iframe-freetoken

🏃

145

Edit photos with a web‑based camera image editor

TTS — Voice-Clone Training Targets

Packaged non-raw reference/target pair shards for public voice-clone training.

instinct-org/audiobook_chunked_speech_restorised_tts_train_clone_pairs

Updated May 21 • 14
instinct-org/default_voices_chunked_speech_restorised_tts_train_clone_pairs

Updated May 21 • 13
instinct-org/espeech_podcasts_chunked_speech_restorised_tts_train_clone_pairs

Updated May 21 • 14
instinct-org/miscellaneous_yt_chunked_speech_restorised_tts_train_clone_pairs

Updated May 21 • 26

Speech Sources — Segmented and Chunked

Reusable segmented or chunked speech datasets.

instinct-org/audio_youtube_chunked

Viewer • Updated May 19 • 560k • 59
instinct-org/audiobook_chunked

Viewer • Updated May 19 • 1.29M • 14
instinct-org/cv_chunked

Viewer • Updated Aug 16 • 71.2k • 15
instinct-org/default_voices_chunked

Viewer • Updated May 19 • 134k • 12

STT — Aligned Upstream Candidates

Restored or aligned STT repositories that are not in the validated 14-repository upstream set.

instinct-org/espeech_podcasts_chunked_nfa_aligned

Viewer • Updated May 21 • 231k • 19
instinct-org/espeech_podcasts_chunked_speech_restorised

Viewer • Updated May 21 • 2.48M • 47
instinct-org/miscellaneous_yt_chunked_speech_restorised

Viewer • Updated May 19 • 530k • 52
instinct-org/miscellaneous_yt_chunked_speech_restorised_nfa_aligned

Viewer • Updated May 26 • 528k • 21

STT — Other Candidates

STT-oriented repositories awaiting full lineage and release validation.

instinct-org/pods

Viewer • Updated Jun 6 • 263 • 13
instinct-org/stt_dataset_uzbek

Viewer • Updated May 19 • 907 • 15
instinct-org/uf_hd

Viewer • Updated Jun 8 • 2.25k • 19

Speech Sources — Unchunked

Long-form or minimally processed source speech datasets.

instinct-org/audio_youtube_unchunked

Viewer • Updated May 19 • 9.88k • 26
instinct-org/audiobook_unchunked

Viewer • Updated May 19 • 1.29M • 17
instinct-org/default_voices_unchunked

Viewer • Updated May 19 • 2.88k • 16
instinct-org/educational_unchunked

Viewer • Updated May 19 • 8.3k • 66

HuggingFaceCode/stack-v3-full

52.8 TB

hai-hu/zh-pythia-2.8B

Updated Apr 3
hai-hu/zh-pythia-1.4B

Updated Apr 17
hai-hu/zh-pythia-1B

Updated May 26
hai-hu/zh-pythia-410M

Updated May 19

This Model Safetensors and GGUF: 10 Models

Running on Zero

Agents

Featured

1.19k

FLUX.2 [dev]

💻

1.19k

Generate or edit images from text and optional photos

Running

Agents

145

Omni-image-editor-iframe-freetoken

🏃

145

Edit photos with a web‑based camera image editor

Previous
1
...
2,383
2,384
2,385
2,386
2,387
...
24,734
Next

Company

TOS Privacy About Careers

Website

Models Datasets Spaces Pricing Docs