temporary account

instinct1912's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

liked a dataset about 3 hours ago

ymoslem/MediaSpeech

Viewer • Updated Mar 25, 2024 • 10k • 245 • 16

updated a dataset 4 days ago

instinct-org/multilingual-tts-voice-dataset

Viewer • Updated 4 days ago • 225k • 37

updated 9 collections 4 days ago

Speech Sources — Unchunked

Collection

Long-form or minimally processed source speech datasets. • 11 items • Updated 4 days ago

TTS — Current Training Targets

Collection

Latest prepared _tts_train corpus for each source family. Use for standard TTS training. • 15 items • Updated 4 days ago

Model-specific Encodings and Artifacts

Collection

Tokenizer-, codec-, or model-specific derived representations. • 18 items • Updated 4 days ago

STT — Current Training Targets

Collection

Latest published speech-restored leaf for each of the 14 accepted STT source families. • 14 items • Updated 4 days ago

STT — Validated Upstream Inputs

Collection

The 14 upstream repositories used by the completed STT training run. These are not final immutable training releases. • 14 items • Updated 4 days ago

Speech Sources — Segmented and Chunked

Collection

Reusable segmented or chunked speech datasets. • 10 items • Updated 4 days ago

TTS — Raw Pair Plans (Not Train-Ready)

Collection

Raw clone-pair planning metadata. These repositories are inputs to consensus and packaging, not training releases. • 11 items • Updated 4 days ago

TTS — Voice-Clone Training Targets

Collection

Packaged non-raw reference/target pair shards for public voice-clone training. • 10 items • Updated 4 days ago

STT — Aligned Upstream Candidates

Collection

Restored or aligned STT repositories that are not in the validated 14-repository upstream set. • 9 items • Updated 4 days ago