Akjava commited on
Commit
932d1cb
·
verified ·
1 Parent(s): fa49b5d

Upload folder using huggingface_hub

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
.gitattributes CHANGED
@@ -1,35 +1,36 @@
1
- *.7z filter=lfs diff=lfs merge=lfs -text
2
- *.arrow filter=lfs diff=lfs merge=lfs -text
3
- *.bin filter=lfs diff=lfs merge=lfs -text
4
- *.bz2 filter=lfs diff=lfs merge=lfs -text
5
- *.ckpt filter=lfs diff=lfs merge=lfs -text
6
- *.ftz filter=lfs diff=lfs merge=lfs -text
7
- *.gz filter=lfs diff=lfs merge=lfs -text
8
- *.h5 filter=lfs diff=lfs merge=lfs -text
9
- *.joblib filter=lfs diff=lfs merge=lfs -text
10
- *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
- *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
- *.model filter=lfs diff=lfs merge=lfs -text
13
- *.msgpack filter=lfs diff=lfs merge=lfs -text
14
- *.npy filter=lfs diff=lfs merge=lfs -text
15
- *.npz filter=lfs diff=lfs merge=lfs -text
16
- *.onnx filter=lfs diff=lfs merge=lfs -text
17
- *.ot filter=lfs diff=lfs merge=lfs -text
18
- *.parquet filter=lfs diff=lfs merge=lfs -text
19
- *.pb filter=lfs diff=lfs merge=lfs -text
20
- *.pickle filter=lfs diff=lfs merge=lfs -text
21
- *.pkl filter=lfs diff=lfs merge=lfs -text
22
- *.pt filter=lfs diff=lfs merge=lfs -text
23
- *.pth filter=lfs diff=lfs merge=lfs -text
24
- *.rar filter=lfs diff=lfs merge=lfs -text
25
- *.safetensors filter=lfs diff=lfs merge=lfs -text
26
- saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
- *.tar.* filter=lfs diff=lfs merge=lfs -text
28
- *.tar filter=lfs diff=lfs merge=lfs -text
29
- *.tflite filter=lfs diff=lfs merge=lfs -text
30
- *.tgz filter=lfs diff=lfs merge=lfs -text
31
- *.wasm filter=lfs diff=lfs merge=lfs -text
32
- *.xz filter=lfs diff=lfs merge=lfs -text
33
- *.zip filter=lfs diff=lfs merge=lfs -text
34
- *.zst filter=lfs diff=lfs merge=lfs -text
35
- *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
5
+ *.ckpt filter=lfs diff=lfs merge=lfs -text
6
+ *.ftz filter=lfs diff=lfs merge=lfs -text
7
+ *.gz filter=lfs diff=lfs merge=lfs -text
8
+ *.h5 filter=lfs diff=lfs merge=lfs -text
9
+ *.joblib filter=lfs diff=lfs merge=lfs -text
10
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
+ *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
+ *.model filter=lfs diff=lfs merge=lfs -text
13
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
14
+ *.npy filter=lfs diff=lfs merge=lfs -text
15
+ *.npz filter=lfs diff=lfs merge=lfs -text
16
+ *.onnx filter=lfs diff=lfs merge=lfs -text
17
+ *.ot filter=lfs diff=lfs merge=lfs -text
18
+ *.parquet filter=lfs diff=lfs merge=lfs -text
19
+ *.pb filter=lfs diff=lfs merge=lfs -text
20
+ *.pickle filter=lfs diff=lfs merge=lfs -text
21
+ *.pkl filter=lfs diff=lfs merge=lfs -text
22
+ *.pt filter=lfs diff=lfs merge=lfs -text
23
+ *.pth filter=lfs diff=lfs merge=lfs -text
24
+ *.rar filter=lfs diff=lfs merge=lfs -text
25
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
26
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
28
+ *.tar filter=lfs diff=lfs merge=lfs -text
29
+ *.tflite filter=lfs diff=lfs merge=lfs -text
30
+ *.tgz filter=lfs diff=lfs merge=lfs -text
31
+ *.wasm filter=lfs diff=lfs merge=lfs -text
32
+ *.xz filter=lfs diff=lfs merge=lfs -text
33
+ *.zip filter=lfs diff=lfs merge=lfs -text
34
+ *.zst filter=lfs diff=lfs merge=lfs -text
35
+ *.wav filter=lfs diff=lfs merge=lfs -text
36
+ *tfevents* filter=lfs diff=lfs merge=lfs -text
README.md CHANGED
@@ -1,3 +1,45 @@
1
  ---
2
  license: mit
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
  license: mit
3
  ---
4
+ This model is a 100-speaker multispeaker model in the Matcha-TTS format/architecture.(trained with Japanese)
5
+
6
+ <div class="audio-container">
7
+ <h4>家具商人のフィシェルは、荷車と仔馬を貸してくれた。</h4>
8
+ <h5>spk10:A lower-pitched female voice with a strong core</h5>
9
+ <audio controls src="https://huggingface.co/Akjava/matcha-tts_ja_100speakers_group006/resolve/main/examples/qwen100_checkpoint_epoch=5874_ch10_kagu.wav"></audio>
10
+ <h4>私はあなたのことが心配です</h4>
11
+ <h5>spk99:A slightly quirky female voice that leaves a strong impression</h5>
12
+ <audio controls src="https://huggingface.co/Akjava/matcha-tts_ja_100speakers_group006/resolve/main/examples/qwen100_checkpoint_epoch=5874_ch99_watashi.wav"></audio>
13
+ <h4>僕はいつか面白いゲームを作りたい</h4>
14
+ <h5>spk26:AI-Game-Bu:SEAN</h5>
15
+ <audio controls src="https://huggingface.co/Akjava/matcha-tts_ja_100speakers_group006/resolve/main/examples/qwen100_checkpoint_epoch=5874_ch26_boku.wav"></audio>
16
+ </div>
17
+
18
+ This model is replaced 10 qwen-character to chatterbox(common voice) character.
19
+
20
+ trained mel_mean/mel_std is difference than group005qw
21
+ ## Qwen3-TTS and Chatterbox Multingual Mixed
22
+ [https://huggingface.co/ResembleAI/chatterbox]
23
+ I faild to confirm watermark because of technical probrom,but maybe chatterbox watermark is exist.
24
+ If you don't like the watermark, use qwen3-tts only version
25
+
26
+ - there are similar [qwen3-tts only](https://huggingface.co/Akjava/matcha-tts_ja_100speakers_group005qw-100) version
27
+
28
+ ## license
29
+ This model license is under MIT
30
+
31
+ My training data is created by Apache Licensed/mit model output.
32
+ https://huggingface.co/Qwen/Qwen3-TTS-12Hz-1.7B-Base
33
+
34
+ Matcha-TTS is MIT
35
+ https://github.com/shivammehta25/Matcha-TTS
36
+
37
+ ## Training
38
+ need checkpoint from there
39
+ https://huggingface.co/Akjava/matcha-tts_ja_100speakers_group003f-CL-V2
40
+
41
+ Use this.
42
+ https://github.com/akjava/Matcha-TTS-Japanese
43
+
44
+ ## Demo
45
+ https://ai-game-bu.itch.io/ai-gaming-voice
checkpoints/README.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ accidentaly 5814 and 5824 is lost
checkpoints/checkpoint_epoch=5819.ckpt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37ca6222c42e0ad9229590a1fb73c9d8395b4306b8a277974bd3dd4b8316a559
3
+ size 250678469
checkpoints/checkpoint_epoch=5829.ckpt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6642a085884c6fd3eb35254815f0fd4a3b543092803fd6330e4d81cf6daf8cb7
3
+ size 250679235
checkpoints/checkpoint_epoch=5834.ckpt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6907644046bc9723f3a1e2108e6a89bced0d938983b2f0066ea010169f03bcf9
3
+ size 250679618
checkpoints/checkpoint_epoch=5839.ckpt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af46e1bab2ab45ce875ba37508c8dfd9bbc71c7cf804fe6bec9915289fca3af6
3
+ size 250680001
checkpoints/checkpoint_epoch=5844.ckpt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:574ea85df2d489e1ab89662102b863561389563aab06c6e803c0f178679fee13
3
+ size 250680384
checkpoints/checkpoint_epoch=5849.ckpt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:605d85b19efbae8521d27f814a889693df8d11ef93abf02db34601e10eb1dfe9
3
+ size 250680767
checkpoints/checkpoint_epoch=5854.ckpt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36407048cac7ccf3a17ca54d78045a054fd42e0f232d91f4a575fbb4eab0aacd
3
+ size 250681150
checkpoints/checkpoint_epoch=5859.ckpt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9da0e90ca1ca7d1ef1abfc19622d1a05ca77d3c1b7274180c4a5fddb68d1f5e
3
+ size 250681342
checkpoints/checkpoint_epoch=5864.ckpt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25258bfb5db12f3c3fb2144e5266adf5b7508256fb5e387a6314228785289180
3
+ size 250681342
checkpoints/checkpoint_epoch=5869.ckpt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dec23f050837076bba2c8be8a0d1a479bc0789f28852443c91cb9f876820b2fb
3
+ size 250681342
checkpoints/checkpoint_epoch=5874.ckpt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53cee1bef01ecdc3bea0416edd69a0878b0d7671e89cb6d187fc39b6800a2906
3
+ size 250681342
configs/data/qwen100.yaml ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ defaults:
2
+ - ljspeech
3
+ - _self_
4
+
5
+ _target_: matcha.data.text_mel_datamodule.TextMelDataModule
6
+ name: vctk
7
+ train_filelist_path: datas/qwen100/train.cleaned.txt
8
+ valid_filelist_path: datas/qwen100/valid.cleaned.txt
9
+ batch_size: 32
10
+ add_blank: True
11
+ n_spks: 100
12
+ data_statistics:
13
+ mel_mean: -5.220970630645752
14
+ mel_std: 2.479220390319824
configs/experiment/qwen100.yaml ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ # @package _global_
2
+
3
+ # to execute this experiment run:
4
+ # python train.py experiment=multispeaker
5
+
6
+ defaults:
7
+ - override /data: qwen100.yaml
8
+
9
+ # all parameters below will be merged with parameters from default configurations set above
10
+ # this allows you to overwrite only specified parameters
11
+
12
+ tags: ["qwen100"]
13
+
14
+ run_name: qwen100
15
+ ckpt_path: group003f-cl-v2_checkpoint_epoch=5709.ckpt
datas/027/001.wav ADDED
Binary file (42.7 kB). View file
 
datas/027/002.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4c29f3b2c8185e8b7feb22ee171ead6c3f308c773566c7842f633be7750c8da
3
+ size 115938
datas/027/003.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b6296241ec75be198ddabd9347aa038623f4b2d6e8688ca8147406023db4492
3
+ size 159862
datas/027/004.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08fcc18d1a1322d05f07b0193f5b49cd660b105a588db655842badc0b6fc0828
3
+ size 103414
datas/027/005.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8e8a7770fa543a8e913fb342a167509a100dd2dcc048bb409b94ab830bc1c39
3
+ size 212254
datas/027/006.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e90a8fbb3bd2956011487fbc5cec27498bcb636234eee0191102e4dd15f2810e
3
+ size 279814
datas/027/007.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb12497c89fb839e28b5e887ce7ad734c1411a9163e5684d0c068d45295bf02d
3
+ size 151394
datas/027/008.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37a9dfd198244bc04dad395ea4dc9d1a85fe6ceb40e2ed5aeb037e94c03d5df2
3
+ size 120348
datas/027/009.wav ADDED
Binary file (97.8 kB). View file
 
datas/027/010.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f3a6b14fb56ef8e20ca459d02282f9a6fe31235a70fd111293e7f269610d663
3
+ size 148572
datas/027/011.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e8dbdd13958fe2e49873c1110ea122f37c601e10f394f4b4f60c09c800df736
3
+ size 272758
datas/027/012.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b27c9a0cd2a2da28f13876c48e52db3cf3a90fd25d6567a5f5ac9b15b6409b2b
3
+ size 145574
datas/027/013.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e4045951de0086d6eeff0ee09d09bfd682652d5170c3cc0177f458032cfeb1a
3
+ size 144162
datas/027/014.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b3e56518df8f60ea2a96d2f8ec44604ce59769e7d77943afe5a1d5614d4e88f
3
+ size 237478
datas/027/015.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b956bb10c773bf9b2a9d0b3a21f735bca5af6b72457f67053df3827fc99b44dc
3
+ size 178208
datas/027/016.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7eda1578195d0c46fe27e24b4219702c5f65e6f2ef9fa13eb031e9eca0cf005f
3
+ size 137284
datas/027/017.wav ADDED
Binary file (55.4 kB). View file
 
datas/027/018.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5da25dffb62e0163e144025dc99bb9054ed0c7e4414ad6a12364c78a29624bbb
3
+ size 139930
datas/027/019.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a18b1441de1d40fc31509e70ab620bcb1bf02c4c784758d89d01e065b8f8458
3
+ size 161274
datas/027/020.wav ADDED
Binary file (51.2 kB). View file
 
datas/027/021.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54cdab4ca08063fdb98146ec146bbeb70cefc8ede46c66b64ed983e4533e25b6
3
+ size 106060
datas/027/022.wav ADDED
Binary file (69.5 kB). View file
 
datas/027/023.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:271fc59018e578bdb3926a5dc9e9788da0d1220142bcc5f2f699a09e39acbcdd
3
+ size 211900
datas/027/024.wav ADDED
Binary file (82.2 kB). View file
 
datas/027/025.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3daf3fefdf9ac8b373b7e169953b10dbb318dcf6dfad5a559671aa1a7cb27f25
3
+ size 199198
datas/027/026.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8fe2daade1b84eda95eb0e9ad574a76f7355b87b7ae55c68ad6d0e8a99755ab
3
+ size 133050
datas/027/027.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8273d53430ba7a2f8e09061a855390c2d8d681af85a6682ffa3ecb9d76e4e8c2
3
+ size 195142
datas/027/028.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc1e3609075323f16f9004b09f959a9c4957397420a8f84be8c97ba529558e3a
3
+ size 140106
datas/027/029.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7afaf8af09574ce0b8a3e529e6debc5f5d3ac1ffa6c6c9fa402ea92dbaac8632
3
+ size 171152
datas/027/030.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2fd4f5c53df766542bf1281d80e2ccdf88f1763aea69f86d08977956cc70732e
3
+ size 178208
datas/027/031.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:838eda1045716c2fd7f44191cc152e9b1dc84a1c2c9fc8dbfb8a54eb7bcfa2e2
3
+ size 144340
datas/027/032.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2c342e19f77f1b37a14daf8c3f18800ba89b2758207a69d8caad7a56ad205b8
3
+ size 195142
datas/027/033.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6df438f327b37899e5f3cdb0bbaf6daacfb3b39f86b70a0785ed8baa6d0b788a
3
+ size 236068
datas/027/034.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2873c9732691eb986c267bdef363f59f5e838e665d9e57a22c0472650df5af4c
3
+ size 144162