replace TTS with supertonic-3

.gitattributes

@@ -36,3 +36,19 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 vlm/qwen2.5-vl-3b-int4/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 mediapipe/face_landmarker.task filter=lfs diff=lfs merge=lfs -text
 mediapipe/gesture_recognizer.task filter=lfs diff=lfs merge=lfs -text
+tts/audio_samples/alphonse_reference.wav filter=lfs diff=lfs merge=lfs -text
+tts/audio_samples/alphonse_supertonic3.wav filter=lfs diff=lfs merge=lfs -text
+tts/audio_samples/keld_reference.wav filter=lfs diff=lfs merge=lfs -text
+tts/audio_samples/keld_supertonic3.wav filter=lfs diff=lfs merge=lfs -text
+tts/audio_samples/luna_reference.wav filter=lfs diff=lfs merge=lfs -text
+tts/audio_samples/luna_supertonic3.wav filter=lfs diff=lfs merge=lfs -text
+tts/audio_samples/moka_reference.wav filter=lfs diff=lfs merge=lfs -text
+tts/audio_samples/moka_supertonic3.wav filter=lfs diff=lfs merge=lfs -text
+tts/audio_samples/nora_reference.wav filter=lfs diff=lfs merge=lfs -text
+tts/audio_samples/nora_supertonic3.wav filter=lfs diff=lfs merge=lfs -text
+tts/audio_samples/watson_reference.wav filter=lfs diff=lfs merge=lfs -text
+tts/audio_samples/watson_supertonic3.wav filter=lfs diff=lfs merge=lfs -text
+tts/img/metrics/runtime_cpu_gpu_latency_memory.png filter=lfs diff=lfs merge=lfs -text
+tts/img/metrics/s3_vs_measured_wer_range_voxcpm2.png filter=lfs diff=lfs merge=lfs -text
+tts/img/metrics/supertonic2_vs_3_comparison.png filter=lfs diff=lfs merge=lfs -text
+tts/img/Supertonic3_HeroImage.png filter=lfs diff=lfs merge=lfs -text

tts/.gitattributes

@@ -1,35 +1,3 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
-*.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
-*.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
 *.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
-*.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
-*.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz 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
+*.png filter=lfs diff=lfs merge=lfs -text
+*.wav filter=lfs diff=lfs merge=lfs -text

tts/.gitignore

@@ -1,4 +1,3 @@
-window.json
-filter_bank.json
-style_extractor.onnx
-*.npy
+.DS_Store
+dev
+.vscode

tts/README.md

@@ -1,162 +1,193 @@
 ---
 license: openrail
 language:
-- en
+    - en
+    - ko
+    - ja
+    - ar
+    - bg
+    - cs
+    - da
+    - de
+    - el
+    - es
+    - et
+    - fi
+    - fr
+    - hi
+    - hr
+    - hu
+    - id
+    - it
+    - lt
+    - lv
+    - nl
+    - pl
+    - pt
+    - ro
+    - ru
+    - sk
+    - sl
+    - sv
+    - tr
+    - uk
+    - vi
 pipeline_tag: text-to-speech
+tags:
+    - text-to-speech
+    - speech-synthesis
+    - tts
+    - onnx
+    - multilingual
+    - on-device
 library_name: supertonic
 ---
 
-# Supertonic — Lightning Fast, On-Device TTS
+# Supertonic 3 | Lightning Fast, On-Device, Accurate TTS
 
-**Supertonic** is a lightning-fast, on-device text-to-speech system designed for **extreme performance** with minimal computational overhead. Powered by ONNX Runtime, it runs entirely on your device—no cloud, no API calls, no privacy concerns.
+![Supertonic 3 Preview](img/Supertonic3_HeroImage.png)
 
-> 🎧 **Try it now**: Experience Supertonic in your browser with our [**Interactive Demo**](https://huggingface.co/spaces/Supertone/supertonic#interactive-demo), or [**Hugging Face app**](https://huggingface.co/spaces/akhaliq/supertonic) or get started with pre-trained models from [**Hugging Face Hub**](https://huggingface.co/Supertone/supertonic)
+<p align="center">
+  <a href="https://huggingface.co/spaces/Supertone/supertonic-3"><img src="https://img.shields.io/badge/Demo-Hugging_Face-yellow?style=for-the-badge" alt="Demo"></a>
+  <a href="https://github.com/supertone-inc/supertonic"><img src="https://img.shields.io/badge/Code-GitHub-black?style=for-the-badge&logo=github" alt="Code"></a>
+  <a href="https://pypi.org/project/supertonic/"><img src="https://img.shields.io/badge/Python-SDK-blue?style=for-the-badge&logo=python" alt="Python SDK"></a>
+</p>
 
-> 🛠 **GitHub Repository**  
-> To use Supertonic most easily, visit the official GitHub repository:  
-> https://github.com/supertone-inc/supertonic  
-> You’ll find multi-language example codes.
+**Supertonic** is a lightweight text-to-speech system for local inference. It runs with ONNX Runtime entirely on your device, with no cloud call required for synthesis.
 
-### Table of Contents
+**Supertonic 3** expands the open-weight release from 5 to **31 languages**, improves reading stability, and reduces repeat/skip failures.
 
-- [Why Supertonic?](#why-supertonic)
-- [Language Support](#language-support)
-- [Getting Started](#getting-started)
-- [Performance](#performance)
-- [Citation](#citation)
-- [License](#license)
+## Quick Start
 
-## Why Supertonic?
+Install the Python SDK and generate speech immediately. On first run, the SDK downloads the model assets from Hugging Face.
 
-- **⚡ Blazingly Fast**: Generates speech up to **167× faster than real-time** on consumer hardware (M4 Pro)—unmatched by any other TTS system
-- **🪶 Ultra Lightweight**: Only **66M parameters**, optimized for efficient on-device performance with minimal footprint
-- **📱 On-Device Capable**: **Complete privacy** and **zero latency**—all processing happens locally on your device
-- **🎨 Natural Text Handling**: Seamlessly processes numbers, dates, currency, abbreviations, and complex expressions without pre-processing
-- **⚙️ Highly Configurable**: Adjust inference steps, batch processing, and other parameters to match your specific needs
-- **🧩 Flexible Deployment**: Deploy seamlessly across servers, browsers, and edge devices with multiple runtime backends.
+```bash
+pip install supertonic
+```
 
+```python
+from supertonic import TTS
 
-## Language Support
+tts = TTS(auto_download=True)
+style = tts.get_voice_style(voice_name="M1")
 
-We provide ready-to-use TTS inference examples across multiple ecosystems:
+text = "A gentle breeze moved through the open window while everyone listened to the story."
+wav, duration = tts.synthesize(text, voice_style=style, lang="en")
 
-| Language/Platform | Path | Description |
-|-------------------|------|-------------|
-| [**Python**] | `py/` | ONNX Runtime inference |
-| [**Node.js**] | `nodejs/` | Server-side JavaScript |
-| [**Browser**] | `web/` | WebGPU/WASM inference |
-| [**Java**] | `java/` | Cross-platform JVM |
-| [**C++**] | `cpp/` | High-performance C++ |
-| [**C#**] | `csharp/` | .NET ecosystem |
-| [**Go**] | `go/` | Go implementation |
-| [**Swift**] | `swift/` | macOS applications |
-| [**iOS**] | `ios/` | Native iOS apps |
-| [**Rust**] | `rust/` | Memory-safe systems |
-| [**Flutter**] | `flutter/` | Cross-platform apps |
+tts.save_audio(wav, "output.wav")
+print(f"Generated {duration:.2f}s of audio")
+```
 
-> For detailed usage instructions, please refer to the README.md in each language directory.
+## What's New in Supertonic 3
 
-## Getting Started
+- **31 languages**: expanded from the 5-language Supertonic 2 release.
+- **More stable reading**: fewer repeat and skip failures, especially on short and long utterances.
+- **Higher speaker similarity**: improved similarity across the shared-language set compared with Supertonic 2.
+- **Expression tags**: supports simple tags such as `<laugh>`, `<breath>`, and `<sigh>`.
 
-First, clone the repository:
+## Custom Voices and Audio Samples
 
-```bash
-git clone https://github.com/supertone-inc/supertonic.git
-cd supertonic
-```
+The open-weight package includes fixed preset voice styles for immediate local inference. If you want to hear how Supertonic 3 performs with zero-shot custom voice styles, visit the [Audio Sample Demo](https://supertonic3.github.io/) to compare reference audio and generated speech across several use cases. To create your own Supertonic 3 voice-style JSON from reference audio, use [Supertonic Voice Builder](https://supertonic.supertone.ai/voice-builder); purchased Voice Builder styles include downloadable embeddings for both Supertonic 2 and Supertonic 3.
 
-### Prerequisites
+Here are a few reference/generated pairs from the audio sample demo:
 
-Before running the examples, download the ONNX models and preset voices, and place them in the `assets` directory:
+**Call center, English**  
+Text: Good morning, thank you for calling. How can I help you today?
 
-```bash
-git clone https://huggingface.co/Supertone/supertonic assets
-```
+| Reference voice | Supertonic 3 output |
+|---|---|
+| <audio controls preload="metadata" src="https://huggingface.co/Supertone/supertonic-3/resolve/main/audio_samples/nora_reference.wav"></audio> | <audio controls preload="metadata" src="https://huggingface.co/Supertone/supertonic-3/resolve/main/audio_samples/nora_supertonic3.wav"></audio> |
+
+**Character voice, Japanese**  
+Text: ふふっ、退屈してたところなの。ちょうどいい遊び相手、見つけたかも♪
+
+| Reference voice | Supertonic 3 output |
+|---|---|
+| <audio controls preload="metadata" src="https://huggingface.co/Supertone/supertonic-3/resolve/main/audio_samples/moka_reference.wav"></audio> | <audio controls preload="metadata" src="https://huggingface.co/Supertone/supertonic-3/resolve/main/audio_samples/moka_supertonic3.wav"></audio> |
+
+**Elder character voice, Korean**  
+Text: 혼자 떠나기엔 길이 험하구나. 이 낡은 검을 가져가거라. 언젠가 어둠이 네 이름을 부르더라도, 부디 빛을 잊지 말거라.
+
+| Reference voice | Supertonic 3 output |
+|---|---|
+| <audio controls preload="metadata" src="https://huggingface.co/Supertone/supertonic-3/resolve/main/audio_samples/alphonse_reference.wav"></audio> | <audio controls preload="metadata" src="https://huggingface.co/Supertone/supertonic-3/resolve/main/audio_samples/alphonse_supertonic3.wav"></audio> |
+
+**Audiobook, English**  
+Text: I was not afraid of silence. I had lived with it long enough to know that, sometimes, it speaks more honestly than people do.
+
+| Reference voice | Supertonic 3 output |
+|---|---|
+| <audio controls preload="metadata" src="https://huggingface.co/Supertone/supertonic-3/resolve/main/audio_samples/luna_reference.wav"></audio> | <audio controls preload="metadata" src="https://huggingface.co/Supertone/supertonic-3/resolve/main/audio_samples/luna_supertonic3.wav"></audio> |
+
+**Audiobook, Japanese**  
+Text: その朝、ロンドンの霧はいつになく低く垂れこめていた。私はただの訪問者だと思っていたが、ホームズの目はすでに別の結論にたどり着いていた。
+
+| Reference voice | Supertonic 3 output |
+|---|---|
+| <audio controls preload="metadata" src="https://huggingface.co/Supertone/supertonic-3/resolve/main/audio_samples/watson_reference.wav"></audio> | <audio controls preload="metadata" src="https://huggingface.co/Supertone/supertonic-3/resolve/main/audio_samples/watson_supertonic3.wav"></audio> |
 
-> **Note:** The Hugging Face repository uses Git LFS. Please ensure Git LFS is installed and initialized before cloning or pulling large model files.
-> - macOS: `brew install git-lfs && git lfs install`
-> - Generic: see `https://git-lfs.com` for installers
+**News, English**  
+Text: Here’s a story worth paying attention to. Supertone has released Supertonic 3, its on-device TTS model. This version expands support to thirty-one languages and improves reading stability.
 
+| Reference voice | Supertonic 3 output |
+|---|---|
+| <audio controls preload="metadata" src="https://huggingface.co/Supertone/supertonic-3/resolve/main/audio_samples/keld_reference.wav"></audio> | <audio controls preload="metadata" src="https://huggingface.co/Supertone/supertonic-3/resolve/main/audio_samples/keld_supertonic3.wav"></audio> |
 
-### Technical Details
+## Performance Highlights
 
-- **Runtime**: ONNX Runtime for cross-platform inference (CPU-optimized; GPU mode is not tested)
-- **Browser Support**: onnxruntime-web for client-side inference
-- **Batch Processing**: Supports batch inference for improved throughput
-- **Audio Output**: Outputs 16-bit WAV files
+Supertonic 3 is designed for practical on-device inference: compact enough to run locally, while staying competitive with much larger open TTS systems.
 
-## Performance
+### Reading Accuracy
 
-We evaluated Supertonic's performance (with 2 inference steps) using two key metrics across input texts of varying lengths: Short (59 chars), Mid (152 chars), and Long (266 chars).
+<p align="center">
+  <img src="img/metrics/s3_vs_measured_wer_range_voxcpm2.png" alt="Supertonic 3 reading accuracy compared with measured model ranges and VoxCPM2">
+</p>
 
-**Metrics:**
-- **Characters per Second**: Measures throughput by dividing the number of input characters by the time required to generate audio. Higher is better.
-- **Real-time Factor (RTF)**: Measures the time taken to synthesize audio relative to its duration. Lower is better (e.g., RTF of 0.1 means it takes 0.1 seconds to generate one second of audio).
+Across measured languages, Supertonic 3 stays within a competitive WER/CER range against much larger open TTS models such as VoxCPM2, while preserving a lightweight on-device deployment path. Asterisked languages use CER; the others use WER.
 
-### Characters per Second
-| System | Short (59 chars) | Mid (152 chars) | Long (266 chars) |
-|--------|-----------------|----------------|-----------------|
-| **Supertonic** (M4 pro - CPU) | 912 | 1048 | 1263 |
-| **Supertonic** (M4 pro - WebGPU) | 996 | 1801 | 2509 |
-| **Supertonic** (RTX4090) | 2615 | 6548 | 12164 |
-| `API` [ElevenLabs Flash v2.5](https://elevenlabs.io/docs/api-reference/text-to-speech/convert) | 144 | 209 | 287 |
-| `API` [OpenAI TTS-1](https://platform.openai.com/docs/guides/text-to-speech) | 37 | 55 | 82 |
-| `API` [Gemini 2.5 Flash TTS](https://ai.google.dev/gemini-api/docs/speech-generation) | 12 | 18 | 24 |
-| `API` [Supertone Sona speech 1](https://docs.supertoneapi.com/en/api-reference/endpoints/text-to-speech) | 38 | 64 | 92 |
-| `Open` [Kokoro](https://github.com/hexgrad/kokoro/) | 104 | 107 | 117 |
-| `Open` [NeuTTS Air](https://github.com/neuphonic/neutts-air) | 37 | 42 | 47 |
+### Supertonic 2 to Supertonic 3
 
-> **Notes:**  
-> `API` = Cloud-based API services (measured from Seoul)  
-> `Open` = Open-source models  
-> Supertonic (M4 pro - CPU) and (M4 pro - WebGPU): Tested with ONNX  
-> Supertonic (RTX4090): Tested with PyTorch model  
-> Kokoro: Tested on M4 Pro CPU with ONNX  
-> NeuTTS Air: Tested on M4 Pro CPU with Q8-GGUF
+<p align="center">
+  <img src="img/metrics/supertonic2_vs_3_comparison.png" alt="Supertonic 2 and Supertonic 3 comparison">
+</p>
 
-### Real-time Factor
+Compared with Supertonic 2, Supertonic 3 reduces repeat and skip failures, improves speaker similarity across the shared-language set, and expands language coverage from 5 to 31 languages.
 
-| System | Short (59 chars) | Mid (152 chars) | Long (266 chars) |
-|--------|-----------------|----------------|-----------------|
-| **Supertonic** (M4 pro - CPU) | 0.015 | 0.013 | 0.012 |
-| **Supertonic** (M4 pro - WebGPU) | 0.014 | 0.007 | 0.006 |
-| **Supertonic** (RTX4090) | 0.005 | 0.002 | 0.001 |
-| `API` [ElevenLabs Flash v2.5](https://elevenlabs.io/docs/api-reference/text-to-speech/convert) | 0.133 | 0.077 | 0.057 |
-| `API` [OpenAI TTS-1](https://platform.openai.com/docs/guides/text-to-speech) | 0.471 | 0.302 | 0.201 |
-| `API` [Gemini 2.5 Flash TTS](https://ai.google.dev/gemini-api/docs/speech-generation) | 1.060 | 0.673 | 0.541 |
-| `API` [Supertone Sona speech 1](https://docs.supertoneapi.com/en/api-reference/endpoints/text-to-speech) | 0.372 | 0.206 | 0.163 |
-| `Open` [Kokoro](https://github.com/hexgrad/kokoro/) | 0.144 | 0.124 | 0.126 |
-| `Open` [NeuTTS Air](https://github.com/neuphonic/neutts-air) | 0.390 | 0.338 | 0.343 |
+### Runtime Footprint
 
-<details>
-<summary><b>Additional Performance Data (5-step inference)</b></summary>
+<p align="center">
+  <img src="img/metrics/runtime_cpu_gpu_latency_memory.png" alt="Supertonic CPU runtime compared with GPU baselines">
+</p>
 
-<br>
+Supertonic 3 runs fast on CPU, even compared with larger baselines measured on A100 GPU, and uses substantially less memory. It does not require a GPU, which makes local, browser, and edge deployment much easier.
 
-**Characters per Second (5-step)**
+### Model Size
 
-| System | Short (59 chars) | Mid (152 chars) | Long (266 chars) |
-|--------|-----------------|----------------|-----------------|
-| **Supertonic** (M4 pro - CPU) | 596 | 691 | 850 |
-| **Supertonic** (M4 pro - WebGPU) | 570 | 1118 | 1546 |
-| **Supertonic** (RTX4090) | 1286 | 3757 | 6242 |
+<p align="center">
+  <img src="img/metrics/model_size_comparison.png" alt="Model size comparison">
+</p>
 
-**Real-time Factor (5-step)**
+At about 99M parameters across the public ONNX assets, Supertonic 3 is much smaller than 0.7B to 2B class open TTS systems. The smaller model size is a practical advantage for download size, startup time, and on-device inference.
 
-| System | Short (59 chars) | Mid (152 chars) | Long (266 chars) |
-|--------|-----------------|----------------|-----------------|
-| **Supertonic** (M4 pro - CPU) | 0.023 | 0.019 | 0.018 |
-| **Supertonic** (M4 pro - WebGPU) | 0.024 | 0.012 | 0.010 |
-| **Supertonic** (RTX4090) | 0.011 | 0.004 | 0.002 |
+## Supported Languages
 
-</details>
+| Code | Language | Code | Language | Code | Language | Code | Language |
+|------|----------|------|----------|------|----------|------|----------|
+| `en` | English | `ko` | Korean | `ja` | Japanese | `ar` | Arabic |
+| `bg` | Bulgarian | `cs` | Czech | `da` | Danish | `de` | German |
+| `el` | Greek | `es` | Spanish | `et` | Estonian | `fi` | Finnish |
+| `fr` | French | `hi` | Hindi | `hr` | Croatian | `hu` | Hungarian |
+| `id` | Indonesian | `it` | Italian | `lt` | Lithuanian | `lv` | Latvian |
+| `nl` | Dutch | `pl` | Polish | `pt` | Portuguese | `ro` | Romanian |
+| `ru` | Russian | `sk` | Slovak | `sl` | Slovenian | `sv` | Swedish |
+| `tr` | Turkish | `uk` | Ukrainian | `vi` | Vietnamese | | |
 
 ## License
 
-This project’s sample code is released under the MIT License. - see the [LICENSE](https://github.com/supertone-inc/supertonic?tab=MIT-1-ov-file) for details.
+This project's sample code is released under the MIT License. See the [GitHub repository](https://github.com/supertone-inc/supertonic) for details.
 
-The accompanying model is released under the OpenRAIL-M License. - see the [LICENSE](https://huggingface.co/Supertone/supertonic/blob/main/LICENSE) file for details.
+The accompanying model is released under the OpenRAIL-M License. See the [LICENSE](https://huggingface.co/Supertone/supertonic-3/blob/main/LICENSE) file in this repository for details.
 
-This model was trained using PyTorch, which is licensed under the BSD 3-Clause License but is not redistributed with this project. - see the [LICENSE](https://docs.pytorch.org/FBGEMM/general/License.html) for details.
+This model was trained using PyTorch, which is licensed under the BSD 3-Clause License but is not redistributed with this project. See the [PyTorch license](https://docs.pytorch.org/FBGEMM/general/License.html) for details.
 
-Copyright (c) 2025 Supertone Inc.
+Copyright (c) 2026 Supertone Inc.

tts/audio_samples/alphonse_reference.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09e613442124ee0cb31146431bbe0b3acd727569a55fc0ae4b4082b5de27c9f3
+size 1152044

tts/audio_samples/alphonse_supertonic3.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3dacbfa5695d6416fb46a3ea72e202e16a467a4cb5ead9425073ef83596811c
+size 970796

tts/audio_samples/keld_reference.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d7f3c2b15ee6ebafe88307658bf0787d3ca19f6347fd9e936e7bff786d1f70a
+size 1152044

tts/audio_samples/keld_supertonic3.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:818c2b25bbf3e568ae8d4aeea5441605ed3e124ab28d746928972066902b35d9
+size 1148972

tts/audio_samples/luna_reference.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1fcec63c22ad76711ec9835a6ca21cb84227045e3aad808f841bcbec455a9470
+size 1152044

tts/audio_samples/luna_supertonic3.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34527bf7ed968ebc5024f985d48ccf06c5c4418fb2d7fc7e3fb7a873e367c273
+size 712748

tts/audio_samples/moka_reference.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad50e1f13c18aa6af2e0f518714675c03ed98f0e85653a642527f56c2d181a56
+size 480044

tts/audio_samples/moka_supertonic3.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bec7d6a5261240935d8436f3ada17aa50774878e8e6ad1696d131e4ec4ecd5f3
+size 479276

tts/audio_samples/nora_reference.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a59576e7ffe84093439924f14d7070fb8174f8306c27049c00e63d747434a772
+size 264644

tts/audio_samples/nora_supertonic3.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d11415a428949df69191361b9dc5f567aaf6eccd89c13013c2fbb381b353321
+size 374828

tts/audio_samples/watson_reference.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5449908651219298eab47a32a04b96291baceea00e772ea9cb16853a93127c30
+size 2304044

tts/audio_samples/watson_supertonic3.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8ffb0051f00e3f6476694604a3d21f6e87b3570b9b73fc2fdb9560c9e6f1c67
+size 1019948

tts/config.json

@@ -1,5 +1,5 @@
 {
-  "model_name": "Supertonic",
+  "model_name": "Supertonic 3",
   "model_type": "onnx",
   "description": "This is a stub config for Hugging Face download counting. The actual model is located at onnx/"
-}
+}

tts/onnx/duration_predictor.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b861580c56a0cba2a2b82aa697ecb3c5a163c3240c60a0ddfac369d21d054092
-size 1500789
+oid sha256:c3eb91414d5ff8a7a239b7fe9e34e7e2bf8a8140d8375ffb14718b1c639325db
+size 3700147

tts/onnx/text_encoder.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba0c8ea74aeb5df00d21a89b8d47c71317f47120232e3deef95024dba37dbd88
-size 27348373
+oid sha256:c7befd5ea8c3119769e8a6c1486c4edc6a3bc8365c67621c881bbb774b9902ff
+size 36416150

tts/onnx/tts.json

@@ -1,12 +1,6 @@
 {
-    "tts_version": "v1.5.0",
-    "split": "opensource-en",
-    "ttl_ckpt_path": "unknown.pt",
-    "dp_ckpt_path": "unknown.pt",
-    "ae_ckpt_path": "unknown.pt",
-    "ttl_train": "unknown",
-    "dp_train": "unknown",
-    "ae_train": "unknown",
+    "tts_version": "v1.7.3",
+    "split": "opensource-multilingual",
     "ttl": {
         "latent_dim": 24,
         "chunk_compress_factor": 6,
@@ -17,9 +11,9 @@
             "scale": 0.25
         },
         "text_encoder": {
-            "char_dict_path": "resources/metadata/char_dict/opensource-en/char_dict.json",
+            "n_langs": 0,
+            "lang_emb_dim": 0,
             "text_embedder": {
-                "char_dict_path": "resources/metadata/char_dict/opensource-en/char_dict.json",
                 "char_emb_dim": 256
             },
             "convnext": {
@@ -30,10 +24,10 @@
                 "dilation_lst": [
                     1,
                     1,
-                    1,
-                    1,
-                    1,
-                    1
+                    2,
+                    2,
+                    4,
+                    4
                 ]
             },
             "attn_encoder": {
@@ -49,7 +43,7 @@
             }
         },
         "flow_matching": {
-            "sig_min": 0
+            "sig_min": 1e-08
         },
         "style_encoder": {
             "proj_in": {
@@ -97,6 +91,8 @@
             "style_value_dim": 256
         },
         "vector_field": {
+            "n_langs": 0,
+            "lang_emb_dim": 0,
             "proj_in": {
                 "ldim": 24,
                 "chunk_compress_factor": 6,
@@ -119,7 +115,8 @@
                 "text_cond_layer": {
                     "idim": 512,
                     "text_dim": 256,
-                    "n_heads": 4,
+                    "n_heads": 8,
+                    "n_units": 512,
                     "use_residual": true,
                     "rotary_base": 10000,
                     "rotary_scale": 10
@@ -127,7 +124,7 @@
                 "convnext_0": {
                     "idim": 512,
                     "ksz": 5,
-                    "intermediate_dim": 1024,
+                    "intermediate_dim": 2048,
                     "num_layers": 4,
                     "dilation_lst": [
                         1,
@@ -139,7 +136,7 @@
                 "convnext_1": {
                     "idim": 512,
                     "ksz": 5,
-                    "intermediate_dim": 1024,
+                    "intermediate_dim": 2048,
                     "num_layers": 1,
                     "dilation_lst": [
                         1
@@ -148,7 +145,7 @@
                 "convnext_2": {
                     "idim": 512,
                     "ksz": 5,
-                    "intermediate_dim": 1024,
+                    "intermediate_dim": 2048,
                     "num_layers": 1,
                     "dilation_lst": [
                         1
@@ -158,7 +155,7 @@
             "last_convnext": {
                 "idim": 512,
                 "ksz": 5,
-                "intermediate_dim": 1024,
+                "intermediate_dim": 2048,
                 "num_layers": 4,
                 "dilation_lst": [
                     1,
@@ -246,9 +243,7 @@
         },
         "sentence_encoder": {
             "char_emb_dim": 64,
-            "char_dict_path": "resources/metadata/char_dict/opensource-en/char_dict.json",
             "text_embedder": {
-                "char_dict_path": "resources/metadata/char_dict/opensource-en/char_dict.json",
                 "char_emb_dim": 64
             },
             "convnext": {
@@ -313,4 +308,4 @@
             "n_layer": 2
         }
     }
-}
+}

tts/onnx/tts.yml

@@ -1,223 +0,0 @@
-tts_version: "v1.5.0"
-
-split: "opensource-en"
-
-ttl_ckpt_path: "unknown.pt"
-
-dp_ckpt_path: "unknown.pt"
-
-ae_ckpt_path: "unknown.pt"
-
-ttl_train: "unknown"
-
-dp_train: "unknown"
-
-ae_train: "unknown"
-
-ttl:
-    latent_dim: 24
-    chunk_compress_factor: 6
-    batch_expander:
-        n_batch_expand: 6
-    normalizer:
-        scale: 0.25
-    text_encoder:
-        char_dict_path: "resources/metadata/char_dict/opensource-en/char_dict.json"
-        text_embedder:
-            char_dict_path: "resources/metadata/char_dict/opensource-en/char_dict.json"
-            char_emb_dim: 256
-        convnext:
-            idim: 256
-            ksz: 5
-            intermediate_dim: 1024
-            num_layers: 6
-            dilation_lst: [1, 1, 1, 1, 1, 1]
-        attn_encoder:
-            hidden_channels: 256
-            filter_channels: 1024
-            n_heads: 4
-            n_layers: 4
-            p_dropout: 0.0
-        proj_out:
-            idim: 256
-            odim: 256
-    flow_matching:
-        sig_min: 0
-    style_encoder:
-        proj_in:
-            ldim: 24
-            chunk_compress_factor: 6
-            odim: 256
-        convnext:
-            idim: 256
-            ksz: 5
-            intermediate_dim: 1024
-            num_layers: 6
-            dilation_lst: [1, 1, 1, 1, 1, 1]
-        style_token_layer:
-            input_dim: 256
-            n_style: 50
-            style_key_dim: 256
-            style_value_dim: 256
-            prototype_dim: 256
-            n_units: 256
-            n_heads: 2
-    speech_prompted_text_encoder:
-        text_dim: 256
-        style_dim: 256
-        n_units: 256
-        n_heads: 2
-    uncond_masker:
-        prob_both_uncond: 0.04
-        prob_text_uncond: 0.01
-        std: 0.1
-        text_dim: 256
-        n_style: 50
-        style_key_dim: 256
-        style_value_dim: 256
-    vector_field:
-        proj_in:
-            ldim: 24
-            chunk_compress_factor: 6
-            odim: 512
-        time_encoder:
-            time_dim: 64
-            hdim: 256
-        main_blocks:
-            n_blocks: 4
-            time_cond_layer:
-                idim: 512
-                time_dim: 64
-            style_cond_layer:
-                idim: 512
-                style_dim: 256
-            text_cond_layer:
-                idim: 512
-                text_dim: 256
-                n_heads: 4
-                use_residual: True
-                rotary_base: 10000
-                rotary_scale: 10
-            convnext_0:
-                idim: 512
-                ksz: 5
-                intermediate_dim: 1024
-                num_layers: 4
-                dilation_lst: [1, 2, 4, 8]
-            convnext_1:
-                idim: 512
-                ksz: 5
-                intermediate_dim: 1024
-                num_layers: 1
-                dilation_lst: [1]
-            convnext_2:
-                idim: 512
-                ksz: 5
-                intermediate_dim: 1024
-                num_layers: 1
-                dilation_lst: [1]
-        last_convnext:
-            idim: 512
-            ksz: 5
-            intermediate_dim: 1024
-            num_layers: 4
-            dilation_lst: [1, 1, 1, 1]
-        proj_out:
-            idim: 512
-            chunk_compress_factor: 6
-            ldim: 24
-
-ae:
-    sample_rate: 44100
-    n_delay: 0
-    base_chunk_size: 512
-    chunk_compress_factor: 1
-    ldim: 24
-    encoder:
-        spec_processor:
-            n_fft: 2048
-            win_length: 2048
-            hop_length: 512
-            n_mels: 228
-            sample_rate: 44100
-            eps: 1e-05
-            norm_mean: 0.0
-            norm_std: 1.0
-        ksz_init: 7
-        ksz: 7
-        num_layers: 10
-        dilation_lst: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
-        intermediate_dim: 2048
-        idim: 1253
-        hdim: 512
-        odim: 24
-    decoder:
-        ksz_init: 7
-        ksz: 7
-        num_layers: 10
-        dilation_lst: [1, 2, 4, 1, 2, 4, 1, 1, 1, 1]
-        intermediate_dim: 2048
-        idim: 24
-        hdim: 512
-        head:
-            idim: 512
-            hdim: 2048
-            odim: 512
-            ksz: 3
-
-dp:
-    latent_dim: 24
-    chunk_compress_factor: 6
-    normalizer:
-        scale: 1.0
-    sentence_encoder:
-        char_emb_dim: 64
-        char_dict_path: "resources/metadata/char_dict/opensource-en/char_dict.json"
-        text_embedder:
-            char_dict_path: "resources/metadata/char_dict/opensource-en/char_dict.json"
-            char_emb_dim: 64
-        convnext:
-            idim: 64
-            ksz: 5
-            intermediate_dim: 256
-            num_layers: 6
-            dilation_lst: [1, 1, 1, 1, 1, 1]
-        attn_encoder:
-            hidden_channels: 64
-            filter_channels: 256
-            n_heads: 2
-            n_layers: 2
-            p_dropout: 0.0
-        proj_out:
-            idim: 64
-            odim: 64
-    style_encoder:
-        proj_in:
-            ldim: 24
-            chunk_compress_factor: 6
-            odim: 64
-        convnext:
-            idim: 64
-            ksz: 5
-            intermediate_dim: 256
-            num_layers: 4
-            dilation_lst: [1, 1, 1, 1]
-        style_token_layer:
-            input_dim: 64
-            n_style: 8
-            style_key_dim: 0
-            style_value_dim: 16
-            prototype_dim: 64
-            n_units: 64
-            n_heads: 2
-    predictor:
-        sentence_dim: 64
-        n_style: 8
-        style_dim: 16
-        hdim: 128
-        n_layer: 2
-
-unicode_indexer_path: "/data/public/model/supertonic/tts/v1.5.0/opensource-en/onnx/unicode_indexer.npy"
-unicode_indexer_json_path: "/data/public/model/supertonic/tts/v1.5.0/opensource-en/onnx/unicode_indexer.json"
-window_path: "/data/public/model/supertonic/tts/v1.5.0/opensource-en/onnx/window.json"
-filter_bank_path: "/data/public/model/supertonic/tts/v1.5.0/opensource-en/onnx/filter_bank.json"

tts/onnx/vector_estimator.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3f82ecd2e9decc4e2236048b03628a1c1d5f14a792ba274a59b7325107aa6a6
-size 132471364
+oid sha256:883ac868ea0275ef0e991524dc64f16b3c0376efd7c320af6b53f5b780d7c61c
+size 256534781

tts/onnx/vocoder.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19bd51f47a186069c752403518a40f7ea4c647455056d2511f7249691ecddf7c
-size 101405066
+oid sha256:085de76dd8e8d5836d6ca66826601f615939218f90e519f70ee8a36ed2a4c4ba
+size 101424195