Aller au contenu
ModelPrésentéExterne
Browse files

Darwin Tts 1.7b Cross GGUF

GGUF conversion of FINAL-Bench/Darwin-TTS-1.7B-Cross for CrispASR.

Sourcehuggingface.co/cstr/darwin-tts-1.7b-cross-GGUF/tree/cbde69869b885425ce9bbc7148faed67e09c5132
TypeOtherModèle de baseFINAL-Bench/Darwin-TTS-1.7B-CrossVersionRevision cbde698BClasse

Source du modèle

Type
Other
Taille du fichier
1,03–3,60 GB
Modèle de base
FINAL-Bench/Darwin-TTS-1.7B-Cross
Version
vRevision cbde698
Mis à jour
26 oct. 2026
Téléchargements
103
Source
Hugging Face

Description de la source

Darwin-TTS-1.7B-Cross — GGUF

GGUF conversion of FINAL-Bench/Darwin-TTS-1.7B-Cross for CrispASR.

Training-free TTS improvement: 3% of a Qwen3-1.7B general LLM's FFN weights are linearly interpolated into the Qwen3-TTS-1.7B backbone, adding emotional expressiveness without any fine-tuning. Runs on the qwen3-tts backend.

Architecture

  • Base: Qwen3-TTS-1.7B pipeline (talker + code predictor + speech tokenizer + codec)
  • Talker (modified): 28-layer Qwen3 LM (2048-dim, 6144 FFN, 16Q/8KV heads) — 84 FFN tensors blended at alpha=3% with Qwen3-1.7B LLM weights
  • Code predictor: 5-layer auxiliary net (1024-dim)
  • Speech tokenizer: 12 Hz RVQ codec
  • Languages: Korean, English, Japanese, Chinese + 6 more

Files

FileSizeDescription
darwin-tts-1.7b-cross-q4_k.gguf1.1 GBQ4_K quantized (recommended)
darwin-tts-1.7b-cross-q8_0.gguf2.0 GBQ8_0 quantized
darwin-tts-1.7b-cross-f16.gguf3.7 GBF16 full precision

Usage

crispasr --backend qwen3-tts \
    -m darwin-tts-1.7b-cross-q4_k.gguf \
    --tts "Hello, world." --tts-output out.wav

License

Apache 2.0 (inherited from Qwen3-TTS and Qwen3-1.7B).

Credits

Provenance and EU AI Act Art. 53 note

  • Upstream model: FINAL-Bench/Darwin-TTS-1.7B-Cross — published by FINAL-Bench.
  • Upstream licence: apache-2.0. This repository redistributes under the same terms; it grants no rights the upstream licence does not.
  • What was done here: format conversion and/or quantisation only (GGUF). No training, no fine-tuning, no merging, no distillation, no change to architecture, vocabulary or capability. Only the numeric representation of the upstream weights differs.
  • Training data: documented — where it is documented at all — by the upstream provider; see the upstream model card. No training data was used, added or selected by this repository. No training-content summary was found on the upstream model card at the time of writing; that documentation gap is upstream's and is not filled here.
  • Provider status: under Regulation (EU) 2024/1689 the upstream authors remain the provider of this model. Converting the serialisation format does not make this repository the provider of a new general-purpose AI model, and no such claim is made. Questions about training content, copyright policy or model capability belong upstream.

Sources

1 source
Hugging FacePrincipalVersion cbde69869b885425ce9bbc7148faed67e09c5132
huggingface.co/cstr/darwin-tts-1.7b-cross-GGUF/tree/cbde69869b885425ce9bbc7148faed67e09c5132

Vérifié 26 oct.

Download files

Artefacts du modèle

3 artefacts

darwin-tts-1.7b-cross-f16.gguf

gguf · 3,60 GB · SHA-256 91c021788e18…ce08 · Hugging Face

Download file

darwin-tts-1.7b-cross-q4_k.gguf

gguf · 1,03 GB · SHA-256 80dc159338fa…dc8f · Hugging Face

Download file

darwin-tts-1.7b-cross-q8_0.gguf

gguf · 1,92 GB · SHA-256 688741f19d64…2c49 · Hugging Face

Download file

Extraits de sources

3 extraits
Readme7 aoûthuggingface.co/cstr/darwin-tts-1.7b-cross-GGUF

--- language: - en - zh - ja - ko license: apache-2.0 tags: - gguf - tts - text-to-speech - qwen3-tts - darwin - crispasr base_model: FINAL-Bench/Darwin-TTS-1.7B-Cross pipeline_tag: text-to-speech --- # Darwin-TTS-1.7B-Cross — GGUF GGUF conversion of [FINAL-Bench/Darwin-TTS-1.7B-Cross](https://huggingface.co/FINAL-Bench/Darwin-TTS-1.7B-Cross) for [CrispASR](https://github.com/CrispStrobe/CrispASR). Training-free TTS improvement: 3% of a Qwen3-1.7B general LLM's FFN weights are linearly interpolated into the Qwen3-TTS-1.7B backbone, adding emotional expressiveness without any fine-tuning. Runs on the `qwen3-tts` backend. ## Architecture - **Base**: Qwen3-TTS-1.7B pipeline (talker + code predictor + speech tokenizer + codec) - **Talker** (modified): 28-layer Qwen3 LM (2048-dim, 6144 FFN, 16Q/8KV heads) — 84 FFN tensors blended at alpha=3% with Qwen3-1.7B LLM weights - **Code predictor**: 5-layer auxiliary net (1024-dim) - **Speech tokenizer**: 12 Hz RVQ codec - **Languages**: Korean, English, Japanese, Chinese + 6 more ## Files | File | Size | Description | |------|------|-------------| | `darwin-tts-1.7b-cross-q4_k.gguf` | 1.1 GB | Q4_K quantized (recommended) | | `darwin-tts-1.7b-cross-q8_0.gguf` | 2.0 GB | Q8_0 quantized | | `darwin-tts-1.7b-cross-f16.gguf` | 3.7 GB | F16 full precision | ## Usage ```bash crispasr --backend qwen3-tts \ -m darwin-tts-1.7b-cross-q4_k.gguf \ --tts "Hello, world." --tts-output out.wav ``` ## License Apache 2.0 (inherited from Qwen3-TTS and Qwen3-1.7B). ## Credits - Original model: [FINAL-Bench](https://huggingface.co/FINAL-Bench/Darwin-TTS-1.7B-Cross) - GGUF conversion & runtime: [CrispASR](https://github.com/CrispStrobe/CrispASR) ## Provenance and EU AI Act Art. 53 note - **Upstream model:** [FINAL-Bench/Darwin-TTS-1.7B-Cross](https://huggingface.co/FINAL-Bench/Darwin-TTS-1.7B-Cross) — published by `FINAL-Bench`. - **Upstream licence:** `apache-2.0`. This repository redistributes under the same terms; it grants no rights the upstream licence does not. - **What was done here:** format conversion and/or quantisation only (GGUF). No training, no fine-tuning, no merging, no distillation, no change to architecture, vocabulary or capability. Only the numeric representation of the upstream weights differs. - **Training data:** documented — where it is documented at all — by the upstream provider; see the...

Note26 oct.huggingface.co/cstr/darwin-tts-1.7b-cross-GGUF

Source context: 103 downloads · 6 likes · Pipeline text-to-speech · Repo cstr/darwin-tts-1.7b-cross-GGUF

Note7 aoûthuggingface.co/cstr/darwin-tts-1.7b-cross-GGUF

Source context: 462 downloads · 4 likes · Pipeline text-to-speech · Repo cstr/darwin-tts-1.7b-cross-GGUF