Add files using upload-large-folder tool

README.md

@@ -0,0 +1,111 @@
+---
+license: other
+license_name: nvidia-open-model-license
+license_link: https://developer.download.nvidia.com/licenses/nvidia-open-model-license-agreement-june-2024.pdf
+language:
+  - en
+  - es
+  - de
+  - fr
+  - it
+  - vi
+  - zh
+  - hi
+  - ja
+tags:
+  - coreml
+  - audio
+  - speech
+  - tts
+  - text-to-speech
+  - multilingual
+  - autoregressive
+  - nano-codec
+  - magpie-tts
+  - quantized
+  - int8
+base_model: nvidia/magpie_tts_multilingual_357m
+library_name: coreml
+pipeline_tag: text-to-speech
+---
+
+# Magpie-TTS-Multilingual-357M-CoreML-8bit
+
+- [speech-swift](https://github.com/soniqo/speech-swift) — Apple SDK
+- [soniqo.audio](https://soniqo.audio) — website
+- [blog](https://soniqo.audio/blog) — blog
+
+Core ML port of [NVIDIA Magpie-TTS Multilingual 357M](https://huggingface.co/nvidia/magpie_tts_multilingual_357m),
+an **autoregressive multi-codebook TTS** model over the [Nano-Codec
+22 kHz / 1.89 kbps / 21.5 fps](https://huggingface.co/nvidia/nemo-nano-codec-22khz-1.89kbps-21.5fps)
+vocoder, quantized to **INT8** weight-only for Apple Silicon.
+
+Core ML INT8 bundle for iOS / macOS.  Four compiled .mlmodelc packages with scatter-based KV cache (fully static graph, ANE-friendly).
+
+## Model
+
+| | |
+|---|---|
+| Total parameters | 357 M (text encoder 99 M + decoder 90 M + LocalTransformer 1 M + NanoCodec 62 M + audio embeddings) |
+| Architecture | Causal Transformer encoder (6L, d=768) + Causal Transformer decoder (12L, d=768) + LocalTransformer codebook AR (1L, d=256) + Causal HiFi-GAN decoder |
+| Audio | 8 codebooks × 2024 codes, 22.05 kHz mono, 21.5 fps |
+| Languages | EN, ES, DE, FR, IT, VI, ZH, HI, JA |
+| Speakers | 5 baked (John, Sofia, Aria, Jason, Leo) |
+| Bundle size | 342 MB on disk |
+| Layout | 4-bundle Core ML (text_encoder / decoder_prefill / decoder_step / nanocodec_decoder) |
+
+## Files
+
+| File | Size | Description |
+|---|---|---|
+| `text_encoder.mlmodelc/` | 97 MB | text encoder (INT8) |
+| `decoder_prefill.mlmodelc/` | 87 MB | decoder prefill (INT8) |
+| `decoder_step.mlmodelc/` | 97 MB | decoder step (INT8) |
+| `nanocodec_decoder.mlmodelc/` | 61 MB | nanocodec decoder (FP16) |
+| `manifest.json` | <1 KB | SHA256 + sizes manifest |
+
+The 4-bundle layout splits the model into:
+
+- **text_encoder** — runs once per utterance over the phoneme sequence
+- **decoder_prefill** — batch-prefills the 110-step baked speaker context into the KV cache (~10× faster than a sequential cold start)
+- **decoder_step** — single AR step over the next audio frame; shares weights with decoder_prefill
+- **nanocodec_decoder** — codes → 22.05 kHz waveform (always FP16; per FluidInference's data, quantizing the codec yields no runtime savings)
+
+## Round-trip validation
+
+End-to-end TTS → faster-whisper large-v3 ASR on a held-out sentence per language (Character Error Rate):
+
+| Language | en | es | de | fr | it | vi | zh | hi |
+|---|---|---|---|---|---|---|---|---|
+| CER | 0.00% | 0.00% | 0.00% | 0.00% | 0.00% | <8% (tone) | <2% (1 added interjection) | mixed-script Whisper artifact |
+
+## Usage
+
+```python
+import json
+from pathlib import Path
+import mlx.core as mx
+
+# 1. Tokenize text in your app (Swift) — see speech-swift's KokoroTTS
+#    pattern. For Japanese, use Apple's CFStringTokenizer + katakana → IPA.
+# 2. Load the 3 sub-models and run the AR loop.
+from huggingface_hub import snapshot_download
+bundle = Path(snapshot_download("aufklarer/Magpie-TTS-Multilingual-357M-CoreML-8bit"))
+
+# Production usage: see https://github.com/soniqo/speech-swift.
+```
+
+The production Swift integration handles tokenization, the AR loop, KV-cache
+management, and audio rendering.  This HuggingFace bundle exists for
+researchers and SDK developers building atop the MLX weights directly.
+
+## Source
+
+- Upstream weights: [nvidia/magpie_tts_multilingual_357m](https://huggingface.co/nvidia/magpie_tts_multilingual_357m) (NVIDIA Open Model License)
+- Codec: [nvidia/nemo-nano-codec-22khz-1.89kbps-21.5fps](https://huggingface.co/nvidia/nemo-nano-codec-22khz-1.89kbps-21.5fps)
+- Paper: [NanoCodec: Towards High-Quality Ultra Fast Speech LLM Inference](https://arxiv.org/abs/2508.05835v1)
+
+## License
+
+**NVIDIA Open Model License** — inherited from upstream Magpie-TTS Multilingual.
+Suitable for commercial use; please review the license text linked above.

decoder_prefill.mlmodelc/analytics/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a71e759209dae88c95a98d201ef52d63d9995561abcf2687885237ec1f02e2c
+size 243

decoder_prefill.mlmodelc/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56f2dcabe4d0e6d563b6c6e3c61547dd307d7a436009ab07ec77172a568db513
+size 1646

decoder_prefill.mlmodelc/weights/weight.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9580baf1d1ab1298b2813c658d5900f67b48ecd469dfe546f41e82203b2ccd7e
+size 90484672

decoder_step.mlmodelc/analytics/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3a90933948f9853bbe4188312427733c0c60ddf15077f06108a8a2f13b6fc9b
+size 243

decoder_step.mlmodelc/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f787fc52103f85c3b0ba92d5f107810aff7ff5ce04034aeba6c434c1e312428
+size 2491

decoder_step.mlmodelc/weights/weight.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d1d0f3402781426161848dd32aed6216ef740cfec8844a8081a7056ccf394d5
+size 101660096

nanocodec_decoder.mlmodelc/analytics/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0577768f9d754fcd4b66bde948bef6b7a8aaa3e63a5a7b611c381a2b24b7dadb
+size 243

nanocodec_decoder.mlmodelc/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f479984a038c5b9054f53db9234e366ea8efb55f295b428ac67d082b86df31a1
+size 373

nanocodec_decoder.mlmodelc/weights/weight.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da987e2d6a5d060cdd27988cc8429a6ee8b2ac612d2758e401686af3629c4392
+size 63178402

text_encoder.mlmodelc/analytics/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a3ae8507cece1fc0d469d6509b20d111f237bc1d56ee6342173b19b0d737e2c
+size 243

text_encoder.mlmodelc/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7224bcea73453e252ca998c1cbc56db2b1a295b0fa6e506e746f8fb59102fbfc
+size 403

text_encoder.mlmodelc/weights/weight.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6c44d18010afb908c0791184468b9f5fbc4c469d7ee8b98eae88e70a67e6a72
+size 101359040