Upload folder using huggingface_hub
Browse files- README.md +22 -0
- kitten-tts-micro-en-v0_8.zip +3 -0
- kitten-tts-mini-en-v0_8.zip +3 -0
- kitten-tts-nano-en-v0_1-fp16.zip +3 -0
- kitten-tts-nano-en-v0_8-fp32.zip +3 -0
- kitten-tts-nano-en-v0_8-int8.zip +3 -0
- manifest.json +93 -0
README.md
ADDED
|
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- text-to-speech
|
| 5 |
+
- sherpa-onnx
|
| 6 |
+
- kitten-tts
|
| 7 |
+
- autodroid
|
| 8 |
+
---
|
| 9 |
+
|
| 10 |
+
# AutoDroid Kitten TTS Models
|
| 11 |
+
|
| 12 |
+
Upload-ready Sherpa ONNX Kitten TTS archives for AutoDroid.
|
| 13 |
+
|
| 14 |
+
Each ZIP contains the files AutoDroid needs after extraction:
|
| 15 |
+
|
| 16 |
+
- model ONNX file
|
| 17 |
+
- voices.bin
|
| 18 |
+
- tokens.txt
|
| 19 |
+
- espeak-ng-data/
|
| 20 |
+
- upstream README and LICENSE from the packaged model folder
|
| 21 |
+
|
| 22 |
+
After uploading these files to Hugging Face, copy the resulting repository commit hash into AutoDroid's voice model catalog/manifest so app downloads are pinned and checksum-verified.
|
kitten-tts-micro-en-v0_8.zip
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:703e335ae3f1f9648c638d31b04986e7d4855d551abe9490fd12370c1eb66b91
|
| 3 |
+
size 45280463
|
kitten-tts-mini-en-v0_8.zip
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2d1b6be5a5fe30f449f90e391dce2cff38ce1596c6bf4b886b3050ddcb47fd33
|
| 3 |
+
size 68558562
|
kitten-tts-nano-en-v0_1-fp16.zip
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f8df2b61ab022b2215777c6358957d9af0be8f1d284b255ea2ee5149e7200dd0
|
| 3 |
+
size 28622954
|
kitten-tts-nano-en-v0_8-fp32.zip
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bc6457c01c71be5532eaeee03ec8c80c5c243cf8f6c42e3f131feba1f7208911
|
| 3 |
+
size 64093040
|
kitten-tts-nano-en-v0_8-int8.zip
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6c77e705fd1fbdb440bb9a8c02f03df0c77d2cf460a239abb0d7d48c8302f226
|
| 3 |
+
size 32708738
|
manifest.json
ADDED
|
@@ -0,0 +1,93 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"schemaVersion": 1,
|
| 3 |
+
"repo": "devendradhakad/kitten-tts",
|
| 4 |
+
"baseResolveUrl": "https://huggingface.co/devendradhakad/kitten-tts/resolve",
|
| 5 |
+
"generatedAt": "2026-06-21T14:27:23+05:30",
|
| 6 |
+
"models": [
|
| 7 |
+
{
|
| 8 |
+
"id": "kitten_tts_mini",
|
| 9 |
+
"displayName": "Kitten TTS Mini",
|
| 10 |
+
"repo": "devendradhakad/kitten-tts",
|
| 11 |
+
"revision": "REPLACE_WITH_HUGGINGFACE_COMMIT_HASH_AFTER_UPLOAD",
|
| 12 |
+
"filename": "kitten-tts-mini-en-v0_8.zip",
|
| 13 |
+
"sizeBytes": 68558562,
|
| 14 |
+
"sha256": "2d1b6be5a5fe30f449f90e391dce2cff38ce1596c6bf4b886b3050ddcb47fd33",
|
| 15 |
+
"archiveRoot": ".",
|
| 16 |
+
"modelFile": "model.onnx",
|
| 17 |
+
"voicesFile": "voices.bin",
|
| 18 |
+
"tokensFile": "tokens.txt",
|
| 19 |
+
"espeakDataDir": "espeak-ng-data",
|
| 20 |
+
"appAssetDir": "kitten-mini-en-v0_8",
|
| 21 |
+
"sourceBytes": 99550582,
|
| 22 |
+
"sourceFileCount": 360
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"id": "kitten_tts_micro",
|
| 26 |
+
"displayName": "Kitten TTS Micro",
|
| 27 |
+
"repo": "devendradhakad/kitten-tts",
|
| 28 |
+
"revision": "REPLACE_WITH_HUGGINGFACE_COMMIT_HASH_AFTER_UPLOAD",
|
| 29 |
+
"filename": "kitten-tts-micro-en-v0_8.zip",
|
| 30 |
+
"sizeBytes": 45280463,
|
| 31 |
+
"sha256": "703e335ae3f1f9648c638d31b04986e7d4855d551abe9490fd12370c1eb66b91",
|
| 32 |
+
"archiveRoot": ".",
|
| 33 |
+
"modelFile": "model.onnx",
|
| 34 |
+
"voicesFile": "voices.bin",
|
| 35 |
+
"tokensFile": "tokens.txt",
|
| 36 |
+
"espeakDataDir": "espeak-ng-data",
|
| 37 |
+
"appAssetDir": "kitten-micro-en-v0_8",
|
| 38 |
+
"sourceBytes": 62667538,
|
| 39 |
+
"sourceFileCount": 360
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"id": "kitten_tts_nano_fp16",
|
| 43 |
+
"displayName": "Kitten TTS Nano FP16",
|
| 44 |
+
"repo": "devendradhakad/kitten-tts",
|
| 45 |
+
"revision": "REPLACE_WITH_HUGGINGFACE_COMMIT_HASH_AFTER_UPLOAD",
|
| 46 |
+
"filename": "kitten-tts-nano-en-v0_1-fp16.zip",
|
| 47 |
+
"sizeBytes": 28622954,
|
| 48 |
+
"sha256": "f8df2b61ab022b2215777c6358957d9af0be8f1d284b255ea2ee5149e7200dd0",
|
| 49 |
+
"archiveRoot": ".",
|
| 50 |
+
"modelFile": "model.fp16.onnx",
|
| 51 |
+
"voicesFile": "voices.bin",
|
| 52 |
+
"tokensFile": "tokens.txt",
|
| 53 |
+
"espeakDataDir": "espeak-ng-data",
|
| 54 |
+
"appAssetDir": "kitten-nano-en-v0_1-fp16",
|
| 55 |
+
"sourceBytes": 41861647,
|
| 56 |
+
"sourceFileCount": 360
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"id": "kitten_tts_nano",
|
| 60 |
+
"displayName": "Kitten TTS Nano FP32",
|
| 61 |
+
"repo": "devendradhakad/kitten-tts",
|
| 62 |
+
"revision": "REPLACE_WITH_HUGGINGFACE_COMMIT_HASH_AFTER_UPLOAD",
|
| 63 |
+
"filename": "kitten-tts-nano-en-v0_8-fp32.zip",
|
| 64 |
+
"sizeBytes": 64093040,
|
| 65 |
+
"sha256": "bc6457c01c71be5532eaeee03ec8c80c5c243cf8f6c42e3f131feba1f7208911",
|
| 66 |
+
"archiveRoot": ".",
|
| 67 |
+
"modelFile": "model.fp32.onnx",
|
| 68 |
+
"voicesFile": "voices.bin",
|
| 69 |
+
"tokensFile": "tokens.txt",
|
| 70 |
+
"espeakDataDir": "espeak-ng-data",
|
| 71 |
+
"appAssetDir": "kitten-nano-en-v0_8-fp32",
|
| 72 |
+
"sourceBytes": 78049671,
|
| 73 |
+
"sourceFileCount": 360
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"id": "kitten_tts_nano_int8",
|
| 77 |
+
"displayName": "Kitten TTS Nano Int8",
|
| 78 |
+
"repo": "devendradhakad/kitten-tts",
|
| 79 |
+
"revision": "REPLACE_WITH_HUGGINGFACE_COMMIT_HASH_AFTER_UPLOAD",
|
| 80 |
+
"filename": "kitten-tts-nano-en-v0_8-int8.zip",
|
| 81 |
+
"sizeBytes": 32708738,
|
| 82 |
+
"sha256": "6c77e705fd1fbdb440bb9a8c02f03df0c77d2cf460a239abb0d7d48c8302f226",
|
| 83 |
+
"archiveRoot": ".",
|
| 84 |
+
"modelFile": "model.int8.onnx",
|
| 85 |
+
"voicesFile": "voices.bin",
|
| 86 |
+
"tokensFile": "tokens.txt",
|
| 87 |
+
"espeakDataDir": "espeak-ng-data",
|
| 88 |
+
"appAssetDir": "kitten-nano-en-v0_8-int8",
|
| 89 |
+
"sourceBytes": 45652547,
|
| 90 |
+
"sourceFileCount": 360
|
| 91 |
+
}
|
| 92 |
+
]
|
| 93 |
+
}
|