| Junco v0.1 (flockspeech/junco) | |
| Copyright 2026 Flock Speech | |
| Licensed under the Apache License, Version 2.0 (see LICENSE). This covers the Junco acoustic model weights | |
| (onnx/encoder.onnx, onnx/decoder-int8.onnx) and the model configuration (onnx/junco.json). | |
| Third-party components: | |
| - Vocos vocoder (onnx/vocoder.onnx): converted from charactr/vocos-mel-24khz, | |
| Copyright (c) 2023 Charactr Inc., MIT License (see onnx/LICENSE-vocos). | |
| - Training data: LJ Speech Dataset (Keith Ito and Linda Johnson), public domain. | |
| Not included, required at run time to turn text into phonemes: | |
| - espeak-ng (GPL-3.0) and phonemizer (GPL-3.0). The flockspeech pip package installs them as separate | |
| dependencies. | |