Nanite-Labs/nanites-smoky-speech-otis
text-to-speech model by Nanite-Labs
From the publisher
Model card & documentation
Source previewRead the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.
Anonymized, gender-pooled Smoky Mountain English text-to-speech voices — the 1930s regional dialect of the Great Smoky Mountains (NC + TN) as recorded by Joseph Sargent Hall in 1939. Built on Fun-CosyVoice3-0.5B-2512 (Apache-2.0, from FunAudioLLM), fine-tuned separately per gender. Second generation of the Smoky voices: new randomly-sampled speaker pools on the CosyVoice 3 engine (first generation: Earl + Ethel on CosyVoice2). The two pooled voices ship under Appalachian codenames so the identity is a persona, never a single Hall speaker: [10, 8, 9, 12, 13, 15, 11, 6] by val loss. Samples: sample/otis0.wav, sample/otis1.wav, sample/otis2.wav (chatbot-written lines, same three lines as Opal for comparison). [8, 14, 15, 13, 9, 12, 11, 16] by val loss. Samples: sample/opal0.wav, sample/opal1.wav, sample/opal2.wav. In code/config the voices keep functional names smoky-speech-malev2 / smoky-speech-femalev2 with speaker IDs / ; "Otis" and "Opal" are the display/persona names. Hugging Face repos are persona-named: Male v2 is fully disjoint…
Read the full model card ↗ · Preview checked 2026-09-26T08:40:47.795Z
Inside the original model card — Document outline
- nanites-smoky-speech-otis / nanites-smoky-speech-opal
- Personas
- Pools (random subsets, seed 20260925)
- Training
- Evaluation
- Provenance
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Documentation belongs to its respective authors. Reported project/model license: apache-2.0. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
Model overview
Nanite-Labs/nanites-smoky-speech-otis is a text-to-speech model repository published by Nanite-Labs on Hugging Face. A library was not reported.
This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.
Model facts
- Task
- text-to-speech
- Library
- Not reported
- Recent downloads (30 days)
- 0
- Cumulative likes
- 0
- Hugging Face trending score
- 0
- Reported safetensors parameters
- Not reported
- Architecture
- Not reported
- License
- apache-2.0
- Access
- Not gated by Hugging Face
- Created
- 2026-09-26T06:03:08.000Z
- Last modified
- 2026-09-26T06:03:38.000Z
Compatibility and lineage
Reported languages: en
Reported base models: FunAudioLLM/Fun-CosyVoice3-0.5B-2512
Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.
Use and evaluate
Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.
No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.
Source and freshness
Source: Hugging Face Hub. Metadata observed 2026-09-26T06:37:45.751Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.