All datasets / ModelsLab

ModelsLab/midashenglm-gen-training-latents

135 downloads in 30 days0 likesLast modified 23 Aug 2026View on Hugging Face

Permissive or share-alike

The declared licence (cc-by-4.0) is classified as permissive.

Declared licence: cc-by-4.0, from the tagEvidence: README.md at 1435234
Licence files: No licence file at the top level of the repositoryEvidence: file list at 1435234
Declared sources: None listed in the card metadata
Access gated on Hugging Face: No

Each cell links to what was checked: a file, a file list or a Hub record.

Tasks

text-to-audio

Citation text from the card

Released CC-BY-4.0, and derived from two attribution-only sources that must be
credited by anyone using it:

- **LibriTTS-R** ([`mythicinfinity/libritts_r`](https://huggingface.co/datasets/mythicinfinity/libritts_r)),
  CC-BY-4.0 — Koizumi et al., *LibriTTS-R: A Restored Multi-Speaker Text-to-Speech Corpus*.
- **MECAT-Caption** ([`mispeech/MECAT-Caption`](https://huggingface.co/datasets/mispeech/MECAT-Caption)),
  CC-BY-3.0 — the public slice of ACAVCaps, itself derived from ACAV100M.

Because the model's decoder reconstructs audio from these latents at parity with
the source — log-mel L1 of 0.26 against controls at 3.3-4.0, and identical word
error rate — treat this as a faithful encoding of that audio rather than as a
derived feature set, and honour the source licences accordingly.

Base model `mispeech/midashenglm-gen` is Apache 2.0.

All datasets marked Permissive or share-alike | JSON

The same facts for your agent

A free MCP server at mcp.datalicense.uk/mcp. Connect it from an MCP client such as Claude or Cursor.

dataset_licence({ "id": "ModelsLab/midashenglm-gen-training-latents" })
signal: "permissive"
stated_licence: "cc-by-4.0"
sources: 0