Mirror AutoDroid pins from litert-community/Qwen3-TTS-12Hz-0.6B-Base@0eb3b8a47149

AUTODROID_MIRROR.md

@@ -0,0 +1,7 @@
+# AutoDroid artifact mirror
+
+This repository preserves selected, unmodified files from `litert-community/Qwen3-TTS-12Hz-0.6B-Base` at commit `0eb3b8a4714972b065c160faec6a12158caa9dc0`.
+
+Original authorship, licenses, and notices remain applicable. This is an independent availability mirror and does not imply upstream endorsement.
+
+See `AUTODROID_SOURCE.json` for original paths, byte sizes, and SHA-256 digests. Only files required by AutoDroid and upstream documentation are included; this is not a complete training or Transformers checkpoint.

AUTODROID_SOURCE.json

@@ -0,0 +1,113 @@
+{
+  "sourceRepository": "litert-community/Qwen3-TTS-12Hz-0.6B-Base",
+  "sourceRevision": "0eb3b8a4714972b065c160faec6a12158caa9dc0",
+  "purpose": "Unmodified pinned artifacts used by AutoDroid",
+  "licenseReview": {
+    "sourceRevision": "0eb3b8a4714972b065c160faec6a12158caa9dc0",
+    "declaredLicense": "apache-2.0",
+    "evidence": "https://huggingface.co/litert-community/Qwen3-TTS-12Hz-0.6B-Base/blob/0eb3b8a4714972b065c160faec6a12158caa9dc0/README.md",
+    "status": "approved",
+    "reason": "Pinned upstream card permits redistribution. Preserve upstream cards and notices, original authorship, and the applicable license texts; artifact bytes are unmodified.",
+    "additionalFiles": [
+      {
+        "localPath": "tools/hf_mirror/licenses/Apache-2.0.txt",
+        "pathInRepo": "licenses/Apache-2.0.txt",
+        "source": "https://www.apache.org/licenses/LICENSE-2.0.txt",
+        "sha256": "c98068a3b6a564e4c70ab7c2ee2c980725987908909e99915759efa28ac7b533"
+      }
+    ]
+  },
+  "artifacts": [
+    {
+      "repo": "litert-community/Qwen3-TTS-12Hz-0.6B-Base",
+      "revision": "0eb3b8a4714972b065c160faec6a12158caa9dc0",
+      "filename": "codec_partA.tflite",
+      "sizeBytes": 162987924,
+      "sha256": "9d3733c2a4c0a8be734d49cde63f57b9d0bee9308e67df678664d25937499c8c",
+      "source": "app/src/main/java/com/example/autodroid/data/voice/model/VoiceModelCatalog.kt:207"
+    },
+    {
+      "repo": "litert-community/Qwen3-TTS-12Hz-0.6B-Base",
+      "revision": "0eb3b8a4714972b065c160faec6a12158caa9dc0",
+      "filename": "codec_partB.tflite",
+      "sizeBytes": 293705152,
+      "sha256": "3486fafde3a50743ccd7330e5009b5b688eb748fb9c138a255cd17fb1846155f",
+      "source": "app/src/main/java/com/example/autodroid/data/voice/model/VoiceModelCatalog.kt:212"
+    },
+    {
+      "repo": "litert-community/Qwen3-TTS-12Hz-0.6B-Base",
+      "revision": "0eb3b8a4714972b065c160faec6a12158caa9dc0",
+      "filename": "merges.txt",
+      "sizeBytes": 1671839,
+      "sha256": "599bab54075088774b1733fde865d5bd747cbcc7a547c5bc12610e874e26f5e3",
+      "source": "app/src/main/java/com/example/autodroid/data/voice/model/VoiceModelCatalog.kt:247"
+    },
+    {
+      "repo": "litert-community/Qwen3-TTS-12Hz-0.6B-Base",
+      "revision": "0eb3b8a4714972b065c160faec6a12158caa9dc0",
+      "filename": "mtp_folded_int8.tflite",
+      "sizeBytes": 229608368,
+      "sha256": "f5ab8f826e3dd68f14667af422145fe57233b445046e5ef42c01b59f82191b4b",
+      "source": "app/src/main/java/com/example/autodroid/data/voice/model/VoiceModelCatalog.kt:202"
+    },
+    {
+      "repo": "litert-community/Qwen3-TTS-12Hz-0.6B-Base",
+      "revision": "0eb3b8a4714972b065c160faec6a12158caa9dc0",
+      "filename": "tables/codec_embedding_fp32.npy",
+      "sizeBytes": 12583040,
+      "sha256": "47fa9e30f98b1528fc9b332d314f22a32fa33e187509a4d3537f8b2c31199e39",
+      "source": "app/src/main/java/com/example/autodroid/data/voice/model/VoiceModelCatalog.kt:217"
+    },
+    {
+      "repo": "litert-community/Qwen3-TTS-12Hz-0.6B-Base",
+      "revision": "0eb3b8a4714972b065c160faec6a12158caa9dc0",
+      "filename": "tables/mtp_embeddings_fp16.npy",
+      "sizeBytes": 62914688,
+      "sha256": "fea581b6a04f1cbec20b49511c36a00011411ccfba31f89b7571f82fe6b36706",
+      "source": "app/src/main/java/com/example/autodroid/data/voice/model/VoiceModelCatalog.kt:222"
+    },
+    {
+      "repo": "litert-community/Qwen3-TTS-12Hz-0.6B-Base",
+      "revision": "0eb3b8a4714972b065c160faec6a12158caa9dc0",
+      "filename": "tables/text_embedding_fp16.npy",
+      "sizeBytes": 622329984,
+      "sha256": "6fab9de0a8bc144aa3efefdacb5e8292b8499a9ae1d60fcee240bac528b7441e",
+      "source": "app/src/main/java/com/example/autodroid/data/voice/model/VoiceModelCatalog.kt:227"
+    },
+    {
+      "repo": "litert-community/Qwen3-TTS-12Hz-0.6B-Base",
+      "revision": "0eb3b8a4714972b065c160faec6a12158caa9dc0",
+      "filename": "tables/text_projection_fp32.npz",
+      "sizeBytes": 25179078,
+      "sha256": "ebb0f6a7aaacdbc903e825e33480b2da4d4b71c43c90acb0e89988049c77c100",
+      "source": "app/src/main/java/com/example/autodroid/data/voice/model/VoiceModelCatalog.kt:232"
+    },
+    {
+      "repo": "litert-community/Qwen3-TTS-12Hz-0.6B-Base",
+      "revision": "0eb3b8a4714972b065c160faec6a12158caa9dc0",
+      "filename": "talker_int4.tflite",
+      "sizeBytes": 255998768,
+      "sha256": "e03df54e73ed1f88b2ae6d47bbf82dd64ea90a3620d753a0f3c8d6a8d60848db",
+      "source": "app/src/main/java/com/example/autodroid/data/voice/model/VoiceModelCatalog.kt:197"
+    },
+    {
+      "repo": "litert-community/Qwen3-TTS-12Hz-0.6B-Base",
+      "revision": "0eb3b8a4714972b065c160faec6a12158caa9dc0",
+      "filename": "vocab.json",
+      "sizeBytes": 2776833,
+      "sha256": "ca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910",
+      "source": "app/src/main/java/com/example/autodroid/data/voice/model/VoiceModelCatalog.kt:242"
+    },
+    {
+      "repo": "litert-community/Qwen3-TTS-12Hz-0.6B-Base",
+      "revision": "0eb3b8a4714972b065c160faec6a12158caa9dc0",
+      "filename": "voices/demo_speaker.npy",
+      "sizeBytes": 4224,
+      "sha256": "b1527f54f68f44ca98bfddcaa9dc0018deb2db62590c9d2699efabbd0dfc1c3c",
+      "source": "app/src/main/java/com/example/autodroid/data/voice/model/VoiceModelCatalog.kt:237"
+    }
+  ],
+  "preservedDocuments": [
+    "README.md"
+  ]
+}

README.md

@@ -0,0 +1,96 @@
+---
+license: apache-2.0
+base_model: Qwen/Qwen3-TTS-12Hz-0.6B-Base
+pipeline_tag: text-to-speech
+language:
+- en
+- zh
+- ja
+- ko
+- de
+- fr
+- es
+- it
+- pt
+- ru
+tags:
+- litert
+- tflite
+- text-to-speech
+- voice-cloning
+- on-device
+---
+
+# Qwen3-TTS-12Hz-0.6B-Base — LiteRT
+
+[Qwen3-TTS-12Hz-0.6B-Base](https://huggingface.co/Qwen/Qwen3-TTS-12Hz-0.6B-Base) (Apache-2.0) converted to LiteRT (.tflite) for fully on-device text-to-speech with 3-second voice cloning, in 10 languages at 24 kHz.
+
+Qwen3-TTS is a speech LM: a Qwen3-style talker predicts 12.5 Hz frames of 16 codec tokens (first codebook by the talker, 15 residual codebooks by an inner "MTP" transformer), and a neural codec decoder renders PCM. LiteRT-LM's Engine decode loop does not support this generation structure yet, so the model runs as **three LiteRT graphs driven by a host-side loop** (LiteRT Compiled Model pattern). A complete Python reference pipeline and all conversion scripts live in the litert-samples sample: [`compiled_model_api/text_to_speech_lm`](https://github.com/john-rocky/litert-samples/tree/qwen3-tts-sample/compiled_model_api/text_to_speech_lm).
+
+## Quick start (Python, desktop)
+
+```bash
+git clone -b qwen3-tts-sample https://github.com/john-rocky/litert-samples.git
+cd litert-samples/compiled_model_api/text_to_speech_lm/python
+pip install -r requirements.txt
+python synthesize.py --text "Hello from LiteRT running fully on device." --output hello.wav
+```
+
+The script downloads this repository automatically (~1.4 GB for the default int4 configuration) and speaks in the bundled demo voice. Enroll your own voice from ~3 s of audio with the sample's `conversion/extract_speaker_embedding.py`, then pass `--speaker my_voice.npy`.
+
+## Android app
+
+The same sample ships an Android app (Kotlin, Compiled Model API, CPU) under `compiled_model_api/text_to_speech_lm/kotlin_cpu/android/`: build with Android Studio or `./gradlew :app:installDebug`, then run `./install_to_device.sh` to download the model files from this repository and push them to the device. Device-verified on Pixel 8a. With the reference `mtp_fp32` + `codec_decoder_fp32` graphs: RTF ≈ 6.7. The app auto-selects the fast graphs when present: `mtp_folded_int8` drops the MTP from ≈333 to ≈68 ms/frame (~5×), and the split `codec_partA`/`codec_partB` drops the codec from ≈114 to ≈40 ms/frame (~2.5×). Together the end-to-end **RTF falls to ≈2.06** (~3.2× vs the reference graphs), ASR-lossless.
+
+## Files
+
+| File | Size | Role |
+|---|---|---|
+| `talker_int4.tflite` | 256 MB | Talker LM (28-layer Qwen3, prefill_32/prefill_128/decode signatures, KV 1024), blockwise-32 OCTAV int4 weights |
+| `talker_fp32.tflite` | 1.8 GB | fp32 talker; under greedy decoding it reproduces the PyTorch reference token-for-token |
+| `mtp_fp32.tflite` | 440 MB | MTP decode step (5-layer transformer, 17-slot KV cache, 15 lm_heads), invoked 17× per frame — the exact reference graph |
+| `mtp_folded_int8.tflite` | 218 MB | **Fast MTP**: all 16 inner steps × 5 layers folded into one graph (in-graph argmax + embedding gather, KV internal), GPTQ dynamic-int8 weights. One invoke per frame; ~5× faster on device. Drop-in replacement for `mtp_fp32.tflite` |
+| `codec_decoder_fp32.tflite` | 457 MB | Codec decoder (RVQ + 8-layer transformer + causal ConvNet, 64-frame chunks → 24 kHz PCM) |
+| `codec_partA.tflite` / `codec_partB.tflite` | 163 + 294 MB | **Fast codec**: the decoder split at the transformer/convnet boundary. Part A (transformer) runs fp32; Part B (the conv upsampler, ~all the FLOPs) runs with XNNPACK FORCE_FP16 → ~2.5× on device, ASR-identical. Drop-in replacement for `codec_decoder_fp32.tflite` |
+| `tokenizer.json` | 11 MB | Qwen2 BPE tokenizer (Python sample / `tokenizers`) |
+| `vocab.json`, `merges.txt` | 4.5 MB | Same vocabulary in raw form (used by the Android app's Kotlin tokenizer) |
+| `tables/*` | 723 MB | Host-side embedding tables: codec embedding (fp32), 15 MTP embeddings (fp16), text embedding (fp16), text projection MLP (fp32) |
+| `voices/demo_speaker.npy` | 4 KB | Demo voice x-vector (enrolled from the official Qwen3-TTS demo clip) |
+
+## Accuracy
+
+- Each graph is numerically verified against the PyTorch reference: talker bit-exact at torch level and correlation 1.0 / top-1 100% as .tflite; MTP 15/15 greedy tokens; codec decoder correlation 1.0 (max abs diff 1.8e-5).
+- End to end with `talker_fp32` + greedy: token-for-token identical codes to the reference implementation, waveform correlation 1.000000, ASR round-trip returns the input sentence.
+- `talker_int4` (data-free blockwise-32 OCTAV) produces a different but valid sampling trajectory; outputs transcribe identically under ASR round-trip. Channelwise int8/int4 quantization (the tooling default) degenerates on this model family — use blockwise granularity.
+
+## Performance (Apple M4 Max, CPU/XNNPACK)
+
+| Stage | per 80 ms audio frame |
+|---|---|
+| Talker decode (8 threads) | 45–50 ms |
+| MTP inner loop (17 invokes, 1 thread) | ~148 ms |
+| Codec decoder (amortized) | ~10 ms |
+| Total | ~205 ms → RTF ≈ 2.5 |
+
+The MTP inner loop dominates (a 78M-parameter transformer streams its weights 17 times per frame). `mtp_folded_int8.tflite` folds those 17 invokes into one graph and quantizes it: on the M4 Max the MTP drops to ~41 ms/frame, and on a Pixel 8a from ~333 to ~68 ms/frame. The fold is token-identical to the reference; the dynamic-int8 weights give a different-but-intelligible trajectory (ASR round-trip exact). The codec then dominates, and `codec_partA`/`codec_partB` split it so the conv-heavy back half runs in fp16 (~2.5× on device). Together the end-to-end RTF drops from ≈6.7 to ≈2.06 on a Pixel 8a (≈1.44 on M4 Max), ASR-lossless. Conversion scripts: [`export_mtp_folded.py` / `gptq_mtp_folded.py` / `export_codec_split.py`](https://github.com/john-rocky/hf-to-litertlm/tree/main/qwen3tts_work). Remaining lever: the talker (now ~52 ms/frame).
+
+### Android (Pixel 8a)
+
+Android figures use the standard TFLite [`benchmark_model`](https://ai.google.dev/edge/litert/models/measurement) on a **Pixel 8a** (Tensor G3, Android 16) — 5 warm-up runs then 20 timed runs, CPU at 4 threads.
+
+| Graph | GPU (OpenCL) | CPU (XNNPACK, 4 threads) |
+|---|---|---|
+| `mtp_folded_int8.tflite` | 225 ms | 153 ms |
+| `mtp_fp32.tflite` | 113 ms | 27 ms |
+
+Nothing here is faster on the GPU; run this pipeline on the CPU on Android.
+
+## Limitations
+
+- Voice cloning is x-vector mode only (speaker embedding). ICL-mode cloning (reference transcript + codec encoding of the reference audio) additionally needs the codec encoder, which is kept off-device (enrollment-time PyTorch).
+- The prompt prefill is capped at 32 positions (the x-vector prompt is always 10); the KV cache is 1024 (~80 s of audio), generation is capped at 512 frames (~41 s) in the sample.
+- Streaming synthesis (the model's dual-track design supports it) is not implemented in the sample loop yet.
+
+## License
+
+Apache-2.0, inherited from the base model by the Qwen team, Alibaba Group.

codec_partA.tflite

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d3733c2a4c0a8be734d49cde63f57b9d0bee9308e67df678664d25937499c8c
+size 162987924

codec_partB.tflite

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3486fafde3a50743ccd7330e5009b5b688eb748fb9c138a255cd17fb1846155f
+size 293705152

licenses/Apache-2.0.txt

@@ -0,0 +1,171 @@
+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.
+
+"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. 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. "Submitted"
+means any form of electronic, verbal, or written communication sent to the
+Licensor or its representatives, excluding communication 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 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;
+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 copyright statement to Your modifications and may
+provide additional or different license terms and conditions for use,
+reproduction, or distribution of Your modifications, provided that 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.
+
+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 arising as a
+result of this License or out of the use or inability to use the Work, 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.

mtp_folded_int8.tflite

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5ab8f826e3dd68f14667af422145fe57233b445046e5ef42c01b59f82191b4b
+size 229608368

tables/codec_embedding_fp32.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47fa9e30f98b1528fc9b332d314f22a32fa33e187509a4d3537f8b2c31199e39
+size 12583040

tables/mtp_embeddings_fp16.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fea581b6a04f1cbec20b49511c36a00011411ccfba31f89b7571f82fe6b36706
+size 62914688

tables/text_embedding_fp16.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fab9de0a8bc144aa3efefdacb5e8292b8499a9ae1d60fcee240bac528b7441e
+size 622329984

tables/text_projection_fp32.npz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebb0f6a7aaacdbc903e825e33480b2da4d4b71c43c90acb0e89988049c77c100
+size 25179078

talker_int4.tflite

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e03df54e73ed1f88b2ae6d47bbf82dd64ea90a3620d753a0f3c8d6a8d60848db
+size 255998768

voices/demo_speaker.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1527f54f68f44ca98bfddcaa9dc0018deb2db62590c9d2699efabbd0dfc1c3c
+size 4224