Inflect-Nano RLX bundle

Exported Inflect-Nano acoustic + vocoder + frontend for RLX (optional parity fixtures).

Field Value
Hub id eugenehp/inflect-nano-rlx
Kind RLX-native weight bundle (graphs + sidecars ready for rlx-* crates).
RLX crate rlx-inflect-nano
Upstream https://huggingface.co/owensong/Inflect-Nano-v1

Quick start

hf download eugenehp/inflect-nano-rlx --local-dir .
cargo run -p rlx-inflect-nano --release -- --data . --text "Hello!" --out out.wav

File highlights

  • acoustic.safetensors (13.2 MiB)
  • frontend/perceptron_tagger.json (5.4 MiB)
  • vocoder.onnx (4.6 MiB)
  • vocoder_static.onnx (4.6 MiB)
  • vocoder.safetensors (4.5 MiB)
  • frontend/g2p_checkpoint.safetensors (3.2 MiB)
  • acoustic/inflect_acoustic_q4_k.gguf (2.7 MiB)
  • inflect_acoustic_q4_k.gguf (2.7 MiB)
  • frontend/bert/tokenizer.json (694.7 KiB)
  • frontend/symbols.json (2.1 KiB)
  • config.json (1.2 KiB)
  • frontend/bert/tokenizer_config.json (351 B)

Run with RLX

Clone rlx-models, place this repo under weights/tts/inflect-nano-rlx (or pass the path explicitly), then:

cargo run -p rlx-inflect-nano --release -- --data . --text "Hello!" --out out.wav

License

Apache License 2.0 โ€” see LICENSE. Inherit upstream terms when redistributing.

Original weights and authorship: https://huggingface.co/owensong/Inflect-Nano-v1

Maintenance

Cards and LFS attrs are regenerated from the local weights/ tree in rlx-models via python3 scripts/prepare_weights_hf.py.

Downloads last month
82
GGUF
Model size
4.04M params
Architecture
inflect-acoustic
Hardware compatibility
Log In to add your hardware
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support