Hugging Face's logo

Akjava
/
matcha-tts_ja_100speakers_group005qw-025

TensorBoard
ONNX
Japanese
Model card Files
xet
 Metrics Community
Akjava commited on
Commit
3e96912
·
1 Parent(s): f744911

init

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. .gitattributes +1 -0
  2. README.md +30 -0
  3. checkpoints/checkpoint_epoch=5714.ckpt +3 -0
  4. checkpoints/checkpoint_epoch=5719.ckpt +3 -0
  5. checkpoints/checkpoint_epoch=5724.ckpt +3 -0
  6. checkpoints/checkpoint_epoch=5729.ckpt +3 -0
  7. checkpoints/checkpoint_epoch=5734.ckpt +3 -0
  8. checkpoints/checkpoint_epoch=5739.ckpt +3 -0
  9. checkpoints/checkpoint_epoch=5744.ckpt +3 -0
  10. checkpoints/checkpoint_epoch=5749.ckpt +3 -0
  11. configs/data/qwen025.yaml +14 -0
  12. configs/experiment/qwen025.yaml +15 -0
  13. datas/001/001.wav +3 -0
  14. datas/001/002.wav +3 -0
  15. datas/001/003.wav +3 -0
  16. datas/001/004.wav +3 -0
  17. datas/001/005.wav +3 -0
  18. datas/001/006.wav +3 -0
  19. datas/001/007.wav +3 -0
  20. datas/001/008.wav +3 -0
  21. datas/001/009.wav +3 -0
  22. datas/001/010.wav +3 -0
  23. datas/001/011.wav +3 -0
  24. datas/001/012.wav +3 -0
  25. datas/001/013.wav +3 -0
  26. datas/001/014.wav +3 -0
  27. datas/001/015.wav +3 -0
  28. datas/001/016.wav +3 -0
  29. datas/001/017.wav +3 -0
  30. datas/001/018.wav +3 -0
  31. datas/001/019.wav +3 -0
  32. datas/001/020.wav +3 -0
  33. datas/001/021.wav +3 -0
  34. datas/001/022.wav +3 -0
  35. datas/001/023.wav +3 -0
  36. datas/001/024.wav +3 -0
  37. datas/001/025.wav +3 -0
  38. datas/001/026.wav +3 -0
  39. datas/001/027.wav +3 -0
  40. datas/001/028.wav +3 -0
  41. datas/001/029.wav +3 -0
  42. datas/001/030.wav +3 -0
  43. datas/001/031.wav +3 -0
  44. datas/001/032.wav +3 -0
  45. datas/001/033.wav +3 -0
  46. datas/001/034.wav +3 -0
  47. datas/001/035.wav +3 -0
  48. datas/001/036.wav +3 -0
  49. datas/001/037.wav +3 -0
  50. datas/001/038.wav +3 -0
.gitattributes CHANGED
@@ -32,4 +32,5 @@ saved_model/**/* 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
 
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 +1,33 @@
1
  ---
2
  license: mit
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
  license: mit
3
  ---
4
+ This model has 100 slots and 25 speaker use them
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_group005qw-025/resolve/main/examples/qwen025_checkpoint_epoch=5749_ch10_kagu.wav"></audio>
10
+ <h4>これはオンクスで作られた音声です。</h4>
11
+ <h5>spk13:A delicate, fleeting female voice that makes you want to protect her</h5>
12
+ <audio controls src="https://huggingface.co/Akjava/matcha-tts_ja_100speakers_group005qw-025/resolve/main/examples/qwen025_checkpoint_epoch=5749_ch13_onnx.wav"></audio>
13
+ <h4>私の声はどうですか？</h4>
14
+ <h5>spk22:A calm, persuasive female voice</h5>
15
+ <audio controls src="https://huggingface.co/Akjava/matcha-tts_ja_100speakers_group005qw-025/resolve/main/examples/qwen025_checkpoint_epoch=5749_ch22_myvoice.wav"></audio>
16
+ </div>
17
+
18
+ ## license
19
+ My training data is created by Apache Licensed model output.
20
+ https://huggingface.co/Qwen/Qwen3-TTS-12Hz-1.7B-Base
21
+
22
+ Matcha-TTS is MIT
23
+ https://github.com/shivammehta25/Matcha-TTS
24
+
25
+ ## Training
26
+ need checkpoint from there
27
+ https://huggingface.co/Akjava/matcha-tts_ja_100speakers_group003f-CL-V2
28
+
29
+ Use this.
30
+ https://github.com/akjava/Matcha-TTS-Japanese
31
+
32
+ ## Demo
33
+ https://ai-game-bu.itch.io/ai-gaming-voice
checkpoints/checkpoint_epoch=5714.ckpt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:64a817134793d7ce7d822d4f6b7c321a4c2c214fdbe957c462649fa5a6ad1256
3
+ size 250678086
checkpoints/checkpoint_epoch=5719.ckpt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0cbe61b746bb8dad0f250ea1660509abbba3cfc77ed920ba262b1cc6fb97e9e
3
+ size 250678469
checkpoints/checkpoint_epoch=5724.ckpt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1df16ca48ac5cebcb5b666125535309ffc2564552b77a2b3c2923bd8e27ee014
3
+ size 250678852
checkpoints/checkpoint_epoch=5729.ckpt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:330795c4ab4e9316727d348a8055db604d0701e6f515ff60c32bc9e2799c248a
3
+ size 250679235
checkpoints/checkpoint_epoch=5734.ckpt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d63cc38bba2403faa740442334e0847ec06b0d21601a626131ba9f6d8c08f1ed
3
+ size 250679618
checkpoints/checkpoint_epoch=5739.ckpt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf67663d8cc94df34161043566d6e89a2b4cc81ad67d951045bc8e3012ea1afb
3
+ size 250680001
checkpoints/checkpoint_epoch=5744.ckpt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5cfa0043f6ef2e2644fbc603bfacd4203fb632a5b446bdcfeb45d8b25a7cffe3
3
+ size 250680384
checkpoints/checkpoint_epoch=5749.ckpt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bff73a99832b6c23ca17e8d0669bf0ac51dfa005c554b66f20c64d7f2585c87b
3
+ size 250680767
configs/data/qwen025.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/qwen025/train.cleaned.txt
8
+ valid_filelist_path: datas/qwen025/valid.cleaned.txt
9
+ batch_size: 32
10
+ add_blank: True
11
+ n_spks: 100
12
+ data_statistics: # Computed for vctk dataset
13
+ mel_mean: -5.212843605487247
14
+ mel_std: 2.4762101720746355
configs/experiment/qwen025.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: qwen025.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: ["qwen025"]
13
+
14
+ run_name: qwen025
15
+ ckpt_path: group003f-cl-v2_checkpoint_epoch=5709.ckpt
datas/001/001.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8748cad10a5e61f5f1d1263024595813c44fb742f41f43d7ec0ab84f8f2cc7f
3
+ size 59922
datas/001/002.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc975e6fd8a9c62821bf6e97f7c326b61804cc8e0f410fc4c740f61563085775
3
+ size 155054
datas/001/003.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57cec4584f6736b2de403400e5c3fb5ba8644bef8a74fbb0bc932b4c95eb159f
3
+ size 229068
datas/001/004.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b8d9a61e6388538d85b76daa4e8a3f438165e61ab04e41a22babc84ad392e58
3
+ size 140960
datas/001/005.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52c63b17058a6914a1e0f98ce6eaef3c0af1736c74e198e90d487b97e9e5dd32
3
+ size 264318
datas/001/006.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8784f69ce71e364ab6654cb46dbbd96caa7e6d1ff86a823c502c487d2805b3ce
3
+ size 412388
datas/001/007.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6739a14829c30c325a7743e1e37fd8ce8916c3c04bf09d3aaa633d1da9b215dc
3
+ size 214970
datas/001/008.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d8f6362848b1fc51e8053b7a0b83099bf26462145465718564df7d519be1d97
3
+ size 169152
datas/001/009.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b25eddcce4be004a21d25f67622a9f3facd2bd27e2697adb9ee252059079302
3
+ size 155054
datas/001/010.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7d875b807b4d6b061f174ef711ae258bad823b99cedfea1387b0e406270e5dd
3
+ size 137434
datas/001/011.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3927b3ccc0c8d1870341178b3a20e4638e2cfe191193c2c38604a1c109d4b33
3
+ size 465278
datas/001/012.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48bb3f9a36487c1d3119f2dbc0c62a6c06ae3474bb5abacbe513eac52847ce03
3
+ size 204396
datas/001/013.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19f97be5ecd1827e1d022fabae60fcb3dd9d991f0a270499e39a99f7cb8df090
3
+ size 190298
datas/001/014.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00992b66f711a9af963df71d5a1bf317430ba3f19964b4e75d73a67c29a52243
3
+ size 313670
datas/001/015.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:729b1469a918a93c100e3dd5779013a92f2e0b285d8a00f0afc34a8e61fa64c9
3
+ size 288994
datas/001/016.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f07484b47ba1278991df9fbbf87e960a818b8e6e97c7abd3a05341ba59c25708
3
+ size 169152
datas/001/017.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33140d86d6f774757528f80bf0a5b8cf24d89b231deb416d0ad3c903d176be0e
3
+ size 81058
datas/001/018.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7954911618cc671d8e6124dee0ad7c3f542c7989d398a59cafdbd87bfda58ee2
3
+ size 197346
datas/001/019.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:986773355fdab24b05da29792a8fcf3b67153c0435b028e3ac662e4eac4f75a6
3
+ size 257268
datas/001/020.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b0ebcc6efb49782775d2e1bdeb4cd65cbf6540e4a3a7ed5695f9cdbec5f531a
3
+ size 70490
datas/001/021.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80d91d7c7d6b7cacc5c7ff8614699dec60f54549a42ea023f54928a0740e4af8
3
+ size 148008
datas/001/022.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92cd6daa017a05e599716f9554fcd54b5ce75e84bfd30460cf5cccd1bdc57009
3
+ size 81058
datas/001/023.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8dd0e0356a5479eced2de213e234b8e8c7a6a977839f8c30c3d802f87b4be917
3
+ size 338348
datas/001/024.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d04ae4ef313f89beb59bafeaea607ae548701330fc670c79562ee8db10af736b
3
+ size 102198
datas/001/025.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfcf8a72174053591a31f6dbb35e2b99dbc5d0d1963c1887a2d8a43c06c88910
3
+ size 348926
datas/001/026.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c850432162d13535a05845e7b6a802a515af0fa345a52046fed2df9704b331c
3
+ size 183250
datas/001/027.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d887c4572bfd092855942c91a7b705c01351834f281b53104733196916fc2de7
3
+ size 278416
datas/001/028.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:276a8d3f0faee703a654dc9e03e73d391b7e60212692deb7283bfa6978073d32
3
+ size 183250
datas/001/029.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ad017bcf886faab6c52705d7c0528685887ef5adcbd7139db29967ca64142dd
3
+ size 288994
datas/001/030.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71ce1feca4a5a4e811f616dca05f209111638e0a8f0d7caef470a1e4d8c74d22
3
+ size 236118
datas/001/031.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a81ca1c7bae0093175a1ff46ba42fe551f6cf8fa3270fc370586657b99e1c8a2
3
+ size 222018
datas/001/032.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:749d44701f6b42a2398cce1aa31cfea7ef3ed7a3ffcfdc1934a7c65800957a17
3
+ size 271366
datas/001/033.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:916fca043d9e4fde14c16c830341dda630e47455bc5a1dc7529407abc4d341b6
3
+ size 267842
datas/001/034.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7b21290ec607dcc7863654ce8642dd7ff6bf2c824b16497d2d5beb092e86f5c
3
+ size 197346
datas/001/035.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3938ed812598cc7c3204e020f53ffb1a567cb6383ff2ecbb9dcc430ad7ea9bf4
3
+ size 204396
datas/001/036.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:efa12ef4838b508e435446d3a15b35cde8216b3d18556810ec2a8fa782cb466d
3
+ size 225542
datas/001/037.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1884f581ed3601fd9d50ad4d57349597c90075d3d6dbc9e48b9c503e9e61c05c
3
+ size 169152
datas/001/038.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4057b930232d91eaa62829491a16ac90c12bef7b07df391ae7f39a0250643259
3
+ size 278416