| [日本語](README.md) |
|
|
| # SBV2 Core ML shared BERT and dictionary |
|
|
| Use this shared Japanese BERT/dictionary with the [SDK and samples](https://github.com/Corvelis/sbv2-coreml) and a separate [voice model](https://huggingface.co/AILogDev/sbv2-coreml-jvnv-f1-jp). |
|
|
| ## Choose a variant |
|
|
| **`int8/` contains INT8; `float32/` contains original FP32.** Each folder includes BERT, the dictionary, licenses and its download manifest. |
| Both variants use the same compatible voice models. |
|
|
| | Variant and files | Shared size | With JVNV | Choose when | App manifest | |
| |---|---:|---:|---|---| |
| | [INT8](https://huggingface.co/AILogDev/sbv2-coreml-common/tree/973d6e239af305f0d78a8bf30c6af5093c0fd47d/int8) | About 503 MB | About 797 MB | Storage size matters | [Download INT8](https://huggingface.co/AILogDev/sbv2-coreml-common/resolve/973d6e239af305f0d78a8bf30c6af5093c0fd47d/int8/download.json) | |
| | [Original FP32](https://huggingface.co/AILogDev/sbv2-coreml-common/tree/973d6e239af305f0d78a8bf30c6af5093c0fd47d/float32) | About 1.52 GB | About 1.81 GB | Avoiding weight quantization or shorter preparation matters | [Download FP32](https://huggingface.co/AILogDev/sbv2-coreml-common/resolve/973d6e239af305f0d78a8bf30c6af5093c0fd47d/float32/download.json) | |
|
|
| INT8 stores BERT weights in 8bit. BERT computation and tensor interfaces are FP32 for both variants. |
| Requires iOS 18+ or macOS 15+ on Apple Silicon. Compilation caches need additional storage; file savings do not establish RAM savings. |
|
|
| ## Download in the sample app |
|
|
| Open **モデル設定 → URLからモデルを取得 → 共通モデル** and choose INT8 or FP32 under **共通モデルの版**. |
| The URL is filled automatically; press **ダウンロード**. For a custom URL or SDK download, use these pinned manifests: |
|
|
| **INT8** |
|
|
| ```text |
| https://huggingface.co/AILogDev/sbv2-coreml-common/resolve/973d6e239af305f0d78a8bf30c6af5093c0fd47d/int8/download.json |
| ``` |
|
|
| **Original FP32** |
|
|
| ```text |
| https://huggingface.co/AILogDev/sbv2-coreml-common/resolve/973d6e239af305f0d78a8bf30c6af5093c0fd47d/float32/download.json |
| ``` |
|
|
| Choose a separate voice and press **モデルを準備** after download. Synthesis works offline. |
|
|
| ## Download one variant on Mac |
|
|
| Use the [Hugging Face CLI](https://huggingface.co/docs/huggingface_hub/guides/cli). |
| Keep `--include`: downloading the entire repository includes both variants and compatibility files. |
|
|
| **INT8 → `models/int8/`** |
|
|
| ```sh |
| hf download AILogDev/sbv2-coreml-common \ |
| --revision 973d6e239af305f0d78a8bf30c6af5093c0fd47d \ |
| --include "int8/*" --local-dir models |
| ``` |
|
|
| **Original FP32 → `models/float32/`** |
|
|
| ```sh |
| hf download AILogDev/sbv2-coreml-common \ |
| --revision 973d6e239af305f0d78a8bf30c6af5093c0fd47d \ |
| --include "float32/*" --local-dir models |
| ``` |
|
|
| Select the downloaded `int8/` or `float32/` root in the sample app. For the SDK, pass its `bert/` and `dictionary/` subfolders and a separate voice folder. |
| Download complete `.mlpackage` contents. |
|
|
| ## Switch models and compare |
|
|
| Stop synthesis/playback, choose the other shared root in **共通モデル**, and press **モデルを準備**. |
| The shared-folder label shows INT8/FP32 from its metadata. Choosing a download variant alone does not switch a prepared model. |
| For the SDK, await completion of existing work, then call `load` and `warmUp` with the selected shared folder. |
| Old folders and caches are not removed automatically. Quit the app or call `unload` before deleting an unused shared folder; retain your separate voice folder. |
|
|
| | iPhone 17 Pro / JVNV Neutral example | INT8 | Original FP32 | |
| |---|---:|---:| |
| | Cached reload + warm-up | About 18 seconds | About 6 seconds | |
| | Warmed median RTF, three sentences | 0.071 | 0.067 | |
|
|
| Initial compilation, playback and concurrent LLM execution are excluded. Texts, voices and devices vary; INT8 is not necessarily faster. |
| BERT rounding can change prosody, timing, duration and waveform. Voice weights and the dictionary are unchanged. |
| No concerning difference was heard in the JVNV Neutral comparison clips; compare your intended voices and texts. |
|
|
| [SDK guide](https://github.com/Corvelis/sbv2-coreml/blob/main/docs/sdk-guide.ja.md) · |
| [Getting started](https://github.com/Corvelis/sbv2-coreml/blob/main/docs/getting-started.ja.md) · |
| [Create compressed shared models](https://github.com/Corvelis/sbv2-coreml/blob/main/docs/compression.md) |
|
|
| ## Previous URLs |
|
|
| Previous pinned URLs remain usable. Root `download.json`, `bert/` and `dictionary/` retain INT8 compatibility for existing URLs. |
| For new downloads, choose `int8/` or `float32/` above. |
|
|
| ## Attribution and terms |
|
|
| BERT derives from Kyoto University's NLP group's [Japanese DeBERTa](https://huggingface.co/ku-nlp/deberta-v2-large-japanese-char-wwm), revision `547b0e8b044fba3f9b84d0ab9f990440bd130c8b`. |
| BERT is **CC BY-SA 4.0**; see each variant's `LICENSE.md` and `provenance.json`. |
| The Open JTalk 1.11 UTF-8 dictionary has separate BSD-style terms in each variant's `dictionary/COPYING`. |
| File hashes are in `checksums.json`. Code is **AGPL-3.0**. This unofficial conversion is not endorsed by the original authors. |
|
|
