Junco v0.1: ONNX release, model card, samples

.gitattributes

@@ -33,3 +33,7 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+samples/assistant.wav filter=lfs diff=lfs merge=lfs -text
+samples/greeting.wav filter=lfs diff=lfs merge=lfs -text
+samples/news.wav filter=lfs diff=lfs merge=lfs -text
+samples/story.wav filter=lfs diff=lfs merge=lfs -text

LICENSE

@@ -0,0 +1,202 @@
+
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

NOTICE

@@ -0,0 +1,16 @@
+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.

README.md

@@ -0,0 +1,272 @@
+---
+license: apache-2.0
+language:
+  - en
+library_name: onnx
+pipeline_tag: text-to-speech
+tags:
+  - text-to-speech
+  - tts
+  - speech-synthesis
+  - onnx
+  - flow-matching
+  - on-device
+  - edge
+  - offline
+  - cpu
+datasets:
+  - keithito/lj_speech
+---
+
+# Junco v0.1
+
+**A small English text-to-speech model that runs offline on a CPU.**
+
+Junco is an 11.4M-parameter flow-matching TTS model from [Flock Speech](https://huggingface.co/flockspeech). It turns
+English text into natural 24 kHz speech on an ordinary CPU, faster than real time. It has no GPU, network or PyTorch
+dependency, and the full model is a 44 MB download.
+
+| | |
+|---|---|
+| **Developed by** | Flock Speech |
+| **Model type** | Non-autoregressive TTS: transformer encoder, duration predictor, conditional flow-matching decoder, Vocos vocoder |
+| **Language** | English (US) |
+| **Voices** | 1 (female, read-aloud style) |
+| **Output** | 24 kHz mono audio |
+| **Parameters** | 11.4M acoustic model + 13.5M vocoder |
+| **Download** | 44 MB (ONNX; int8 decoder, fp16 encoder and vocoder) |
+| **Runtime** | ONNX Runtime on CPU (Linux, macOS, Windows; x86-64 and ARM64) |
+| **License** | Apache-2.0 (vocoder weights MIT) |
+| **Version** | v0.1, November 2026 |
+
+## Samples
+
+All samples were made with the files in this repository at default settings (8 steps, seed 0), with no editing.
+
+| Use | Text | Audio |
+|---|---|---|
+| Greeting | *Hello! I'm Junco, a tiny voice that runs entirely on your own device.* | <audio controls src="https://huggingface.co/flockspeech/junco/resolve/main/samples/greeting.wav"></audio> |
+| Assistant | *Your next meeting starts in fifteen minutes. Would you like me to read the agenda?* | <audio controls src="https://huggingface.co/flockspeech/junco/resolve/main/samples/assistant.wav"></audio> |
+| Narration | *The old lighthouse keeper climbed the spiral stairs one last time, and watched the ships come home through the fog.* | <audio controls src="https://huggingface.co/flockspeech/junco/resolve/main/samples/story.wav"></audio> |
+| News | *Researchers announced on Tuesday that the new battery can be charged in under ten minutes, and lasts twice as long.* | <audio controls src="https://huggingface.co/flockspeech/junco/resolve/main/samples/news.wav"></audio> |
+
+## Quick start
+
+The [`flockspeech`](https://pypi.org/project/flockspeech/) Python package bundles these weights, so nothing is downloaded
+at run time.
+
+```sh
+pip install flockspeech
+flockspeech "Hello! I'm Junco." -o hello.wav --play
+```
+
+```python
+from flockspeech import Junco
+
+tts = Junco()                        # loads in under a second
+audio = tts("Hello there.")          # float32 numpy array, 24 kHz mono
+tts.save("Hello there.", "hello.wav")
+
+# Low latency: audio is produced sentence by sentence
+for chunk in tts.stream(long_text):
+    play(chunk)
+```
+
+To use the files in this repository directly:
+
+```python
+from huggingface_hub import snapshot_download
+from flockspeech import Junco
+
+path = snapshot_download("flockspeech/junco", allow_patterns=["onnx/*"])
+tts = Junco(model_dir=f"{path}/onnx")
+```
+
+### Options
+
+| Parameter | Default | Effect |
+|---|---|---|
+| `speed` | 1.0 | Speaking rate; 1.2 is 20% faster |
+| `steps` | 8 | Flow-matching steps; 4 is about 1.5× faster with slightly lower quality |
+| `seed` | 0 | Fixes the small random variation in delivery, so output is reproducible |
+| `threads` | up to 4 | CPU threads for ONNX Runtime |
+
+## Evaluation
+
+We benchmarked Junco against open TTS models of similar purpose. Every model was run with the same harness, on the
+same sentences and the same machine, and scored by the same tools.
+
+**Test set.** 150 sentences from LibriTTS-R test-clean (35 speakers, 6 to 40 words each). None of the models trained on
+them. F5-TTS was scored on a fixed subset of 75 sentences, because it is slow on a CPU.
+
+**Metrics.**
+- **UTMOS22:** predicted naturalness on a 1–5 scale.
+- **UTMOSv2:** a second, independent naturalness predictor.
+- **WER:** word error rate of Whisper large-v3-turbo transcripts, after Whisper's English text normaliser.
+
+### Everyday speech
+
+| Model | Size (MB) | UTMOS22 ↑ | UTMOSv2 ↑ | WER ↓ | License |
+|---|---:|---:|---:|---:|---|
+| Real recordings (reference) | n/a | 4.23 | 3.29 | 2.30% | n/a |
+| **Junco v0.1** | **77.2** † | **4.20** | **3.72** | **1.71%** | **Apache-2.0** |
+| Matcha-TTS | 274.6 | 4.34 | 3.80 | 1.65% | MIT |
+| Piper (lessac, medium) | 63.2 | 4.35 | 3.79 | 2.33% | GPL-3.0 |
+| F5-TTS v1 | 1402.9 | 4.24 | 3.52 | 2.58% | CC BY-NC 4.0 weights |
+| KittenTTS nano 0.1 | 23.9 | 3.59 | 2.02 | 3.12% | Apache-2.0 |
+
+† Benchmark run with the PyTorch checkpoint. The ONNX release in this repository is **44 MB**; see
+[Optimised release](#optimised-release).
+
+Junco's word error rate is lower than that of the real recordings. Its naturalness is close to the real recordings
+(4.20 vs 4.23), but about 0.15 below Piper and Matcha-TTS. On the 92-sentence hard-text set (numbers, dates, money,
+contact details, names, homographs and assistant-style replies), Junco's WER is 4.9%. Piper scored 4.9%, Matcha-TTS 5.2%,
+F5-TTS 7.0% and KittenTTS 9.3%. On one-minute paragraphs, Junco's WER is 0.5%.
+
+### Speed
+
+Speed is measured as seconds of audio produced per second of compute, vocoder included, on 13 typical reply sentences.
+
+| Model | 1 CPU thread ↑ | 4 CPU threads ↑ | NVIDIA T4 GPU ↑ | Peak RAM |
+|---|---:|---:|---:|---:|
+| Piper | 7.4× | 13.5× | n/a | 382 MB |
+| KittenTTS | 3.3× | 5.0× | n/a | 789 MB |
+| **Junco v0.1 (PyTorch)** | **3.1×** | **5.1×** | **33×** | **623 MB** |
+| Matcha-TTS | 0.7× | 1.3× | 25× | 1,453 MB |
+| F5-TTS v1 | 0.006× | 0.011× | 2.1× | 3,698 MB |
+
+The CPU was an Intel Xeon at 2.2 GHz, a slow cloud CPU. Desktop and laptop CPUs are several times faster.
+
+### Optimised release
+
+The ONNX graphs in this repository were checked against the PyTorch model:
+- **Before quantisation:** they match PyTorch to over 78 dB SNR.
+- **After quantisation:** we compared quality and speed on 40 sentences from the same test set, measured on an Apple M1.
+
+| Build | Size | UTMOS22 | 1 thread | 4 threads | Peak RAM |
+|---|---:|---:|---:|---:|---:|
+| fp32 reference | 100 MB | 4.21 | 5.1× | n/a | n/a |
+| **This release** (int8 decoder, fp16 storage) | **44 MB** | **4.18** | **8.7×** | **19×** | **265 MB** |
+| This release, `steps=4` | 44 MB | 4.12 | 13.6× | 27× | 265 MB |
+
+The UTMOS difference between the fp32 reference and this release is −0.03 ± 0.05 (95% confidence interval), which is
+not significant. We quantised only the decoder, which does most of the computation. An int8 vocoder cost 0.15 UTMOS,
+so the vocoder stays at full precision; its weights are stored as fp16 and computed in fp32.
+
+**Latency.** Start-up takes about 0.7 s. When streaming on 4 M1 threads, the first audio arrives about 0.25 s after
+the request.
+
+## Intended use
+
+**Suitable for:**
+- Voice output on devices and in apps that must work offline or keep text private: assistants, accessibility and
+  screen-reading tools, kiosks, robotics, games and embedded products.
+- CPU-only servers where cost or latency matters.
+- Prototyping and research on small TTS models.
+
+**Out of scope:**
+- Languages other than English, or speaker voices other than the one provided. Junco has no voice cloning.
+- Expressive, emotional or conversational styles. The voice reads in a neutral, read-aloud style.
+- Impersonating a real person, or producing audio meant to deceive listeners about who is speaking or whether the
+  speech is synthetic.
+
+## Limitations
+
+- **No text normalisation.** Write numbers, currency, dates and abbreviations in words: "five dollars", not "$5";
+  "Doctor", not "Dr.". Raw digits and symbols are read by espeak-ng's rules, which may not be what you want. Most of
+  Junco's errors on the hard-text set are of this kind:
+  - assistant-style replies: 20% WER;
+  - contact details: 13%;
+  - money: 12%;
+  - names: 11%.
+- **Pronunciation comes from espeak-ng.** Rare names, brands and some homographs, such as *read* and *lead*, can be
+  mispronounced.
+- **One voice, one accent.** The model learned from a single US English speaker.
+- **Long-form audio.** Text is synthesised sentence by sentence. Prosody does not carry across sentences, and
+  naturalness on long paragraphs is lower (UTMOS22 3.88).
+- **Bright high frequencies.** About 14% of Junco's energy lies above 4 kHz, against 2% for real recordings. On some
+  playback systems this may sound slightly bright or hissy.
+- **Automatic metrics only.** The quality figures come from automatic predictors (UTMOS22, UTMOSv2) and Whisper, not
+  from a formal human listening test.
+
+## Risks and responsible use
+
+Synthetic speech can be misused for deception. Junco produces a single fixed voice and cannot clone speakers, which
+limits impersonation risk. We still ask that you:
+- tell listeners when speech is synthetic, where that matters;
+- not use the model for fraud, harassment or deceptive impersonation;
+- review output before you use it in safety-critical or high-stakes settings.
+
+## Model details
+
+### Architecture
+
+The model runs in four stages:
+1. **Text front end:** espeak-ng converts text to IPA phonemes (en-us, with stress marks). A blank token is inserted
+   between phonemes.
+2. **Text encoder (3.2M parameters):** 3 ConvNeXt pre-net blocks, then 6 transformer layers (width 192, RoPE, SwiGLU,
+   RMSNorm). It predicts a per-phoneme mel prior.
+3. **Duration predictor (0.3M parameters):** a convolutional regressor of log-durations. It was trained on alignments from Monotonic
+   Alignment Search, so no external aligner is needed.
+4. **Decoder (7.9M parameters):** a flow-matching U-Net hybrid.
+   - ConvNeXt blocks run at the full frame rate, and four adaLN transformer blocks run at half the frame rate.
+   - It uses classifier-free guidance (weight 1.0) and 8 Euler steps with a sway-sampling schedule.
+   - It outputs a 100-band log-mel spectrogram (hop 256, 24 kHz).
+
+The vocoder is [Vocos](https://huggingface.co/charactr/vocos-mel-24khz) (charactr/vocos-mel-24khz, MIT). In ONNX it
+predicts the STFT magnitude and phase, and the inverse STFT runs in numpy.
+
+### Files
+
+| File | Contents | Size |
+|---|---|---:|
+| `onnx/encoder.onnx` | Text encoder and duration predictor (fp16 weights, fp32 compute) | 7.2 MB |
+| `onnx/decoder-int8.onnx` | One guided flow-matching step (int8 dynamic quantisation) | 9.9 MB |
+| `onnx/vocoder.onnx` | Vocos backbone and spectral head (fp16 weights, fp32 compute) | 27.1 MB |
+| `onnx/junco.json` | Mel normalisation statistics and default inference settings | <1 kB |
+| `samples/` | The audio samples above | |
+
+### Training
+
+| | |
+|---|---|
+| **Data** | [LJ Speech](https://keithito.com/LJ-Speech-Dataset/): 13,100 clips, about 24 hours, one speaker, public domain |
+| **Objective** | Conditional flow matching (logit-normal time sampling, σ_min 1e-4), MAS prior loss, duration MSE |
+| **Guidance** | Condition dropped for 10% of training examples, for classifier-free guidance |
+| **Optimiser** | AdamW (lr 2e-4, β 0.9/0.98, weight decay 0.01), 1,000 warm-up steps, EMA 0.999 |
+| **Batching** | Dynamic batches of up to 20,000 mel frames |
+| **Compute** | 44,485 steps in 3 hours on one NVIDIA T4 GPU |
+| **Released weights** | EMA weights |
+
+**Environmental impact.** The final training run used about 3 GPU-hours on one NVIDIA T4 (70 W TDP), or about
+0.2 kWh. Architecture experiments before it used more.
+
+## License
+
+- **Junco weights and configuration:** [Apache License 2.0](LICENSE). Commercial use, modification and redistribution
+  are allowed.
+- **Vocos vocoder weights** (`onnx/vocoder.onnx`): MIT, © 2023 Charactr Inc. See `onnx/LICENSE-vocos`.
+- **Training data:** LJ Speech, public domain.
+
+**Run-time dependency.** Text-to-phoneme conversion uses espeak-ng and phonemizer. Both are GPL-3.0 and are **not**
+included in this repository. The `flockspeech` package installs them as separate dependencies. If you plan to ship
+Junco inside a closed-source product, review their licence terms, or replace the phonemiser with one under a licence
+that suits you. See [NOTICE](NOTICE).
+
+## Citation
+
+```bibtex
+@misc{flockspeech2026junco,
+  title        = {Junco: a small flow-matching text-to-speech model for on-device use},
+  author       = {{Flock Speech}},
+  year         = {2026},
+  howpublished = {\url{https://huggingface.co/flockspeech/junco}},
+  note         = {Version 0.1}
+}
+```
+
+## Acknowledgements
+
+Junco builds on ideas from Matcha-TTS (conditional flow matching for TTS), Glow-TTS (Monotonic Alignment Search),
+F5-TTS (sway sampling), ZipVoice and SupertonicTTS (efficient decoder design), and Vocos (vocoder). We thank the authors
+of these works and of LJ Speech, LibriTTS-R, UTMOS and Whisper.

onnx/LICENSE-vocos

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2023 Charactr Inc.
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

onnx/decoder-int8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c940fddceb7b22fea2d1c38b4b966fc15774e093152c8c319c7d0ffbfa409cd6
+size 9936441

onnx/encoder.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fae7a6d627b0d33961a78ec302d642b1d609fe68b531f82164a55b277a15e53d
+size 7174680

onnx/junco.json

@@ -0,0 +1,20 @@
+{
+ "name": "junco",
+ "version": "v0.1",
+ "sample_rate": 24000,
+ "hop": 256,
+ "n_fft": 1024,
+ "mean": -1.49140640330624,
+ "std": 2.024339073543612,
+ "defaults": {
+  "n_steps": 8,
+  "cfg_w": 1.0,
+  "temp": 0.667,
+  "sway": -1.0
+ },
+ "files": {
+  "encoder": "encoder.onnx",
+  "decoder": "decoder-int8.onnx",
+  "vocoder": "vocoder.onnx"
+ }
+}

onnx/vocoder.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1781ab9038b0ec7c7b44dc04d00ca8fe60dde0e9215ef73be353628085a18873
+size 27099450

samples/assistant.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a52a29fd3e2e9ef137c46369fd2178e24ef22e4f8a101c43836d9e2811347265
+size 268044

samples/greeting.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c69918794ce88b5648943bd25edfddf45a5fd2d43896182fe2b5c55cf071502
+size 262924

samples/news.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a04fefe11667375467fce19d31ba9d4aeedec83efbdc508acf30315369c3e1e1
+size 365612

samples/story.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e99fd273aaf04ec4f7d66128f082f665e89ae9dbe14362799b40c8a9302fa6cd
+size 338476