MeloTTS (en, es, fr, ja, ko, ms, vi, zh/en)
Browse filesThis view is limited to 50 files because it contains too many changes. See raw diff
- .gitattributes +44 -0
- en/MeloTTS-English-ax630c/.gitattributes +38 -0
- en/MeloTTS-English-ax630c/README.md +3 -0
- en/MeloTTS-English-ax630c/decoder-en-au.axmodel +3 -0
- en/MeloTTS-English-ax630c/decoder-en-br.axmodel +3 -0
- en/MeloTTS-English-ax630c/decoder-en-default.axmodel +3 -0
- en/MeloTTS-English-ax630c/decoder-en-india.axmodel +3 -0
- en/MeloTTS-English-ax630c/decoder-en-us.axmodel +3 -0
- en/MeloTTS-English-ax630c/en_tn_tagger.fst +3 -0
- en/MeloTTS-English-ax630c/en_tn_verbalizer.fst +3 -0
- en/MeloTTS-English-ax630c/encoder-en.onnx +3 -0
- en/MeloTTS-English-ax630c/g-en-au.bin +3 -0
- en/MeloTTS-English-ax630c/g-en-br.bin +3 -0
- en/MeloTTS-English-ax630c/g-en-default.bin +3 -0
- en/MeloTTS-English-ax630c/g-en-india.bin +3 -0
- en/MeloTTS-English-ax630c/g-en-us.bin +3 -0
- en/MeloTTS-English-ax630c/lexicon-en.txt +3 -0
- en/MeloTTS-English-ax630c/source.txt +1 -0
- en/MeloTTS-English-ax630c/tokens-en.txt +219 -0
- en/MeloTTS-English-ax650/.gitattributes +38 -0
- en/MeloTTS-English-ax650/README.md +3 -0
- en/MeloTTS-English-ax650/decoder-en-au.axmodel +3 -0
- en/MeloTTS-English-ax650/decoder-en-br.axmodel +3 -0
- en/MeloTTS-English-ax650/decoder-en-default.axmodel +3 -0
- en/MeloTTS-English-ax650/decoder-en-india.axmodel +3 -0
- en/MeloTTS-English-ax650/decoder-en-us.axmodel +3 -0
- en/MeloTTS-English-ax650/en_tn_tagger.fst +3 -0
- en/MeloTTS-English-ax650/en_tn_verbalizer.fst +3 -0
- en/MeloTTS-English-ax650/encoder-en.onnx +3 -0
- en/MeloTTS-English-ax650/g-en-au.bin +3 -0
- en/MeloTTS-English-ax650/g-en-br.bin +3 -0
- en/MeloTTS-English-ax650/g-en-default.bin +3 -0
- en/MeloTTS-English-ax650/g-en-india.bin +3 -0
- en/MeloTTS-English-ax650/g-en-us.bin +3 -0
- en/MeloTTS-English-ax650/lexicon-en.txt +3 -0
- en/MeloTTS-English-ax650/source.txt +1 -0
- en/MeloTTS-English-ax650/tokens-en.txt +219 -0
- en/MeloTTS-English-v2/.gitattributes +35 -0
- en/MeloTTS-English-v2/README.md +103 -0
- en/MeloTTS-English-v2/checkpoint.pth +3 -0
- en/MeloTTS-English-v2/config.json +189 -0
- en/MeloTTS-English-v2/source.txt +1 -0
- en/MeloTTS-English-v3/.gitattributes +35 -0
- en/MeloTTS-English-v3/README.md +83 -0
- en/MeloTTS-English-v3/checkpoint.pth +3 -0
- en/MeloTTS-English-v3/config.json +293 -0
- en/MeloTTS-English-v3/source.txt +1 -0
- en/MeloTTS-English/.gitattributes +35 -0
- en/MeloTTS-English/README.md +124 -0
- en/MeloTTS-English/checkpoint.pth +3 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,47 @@ saved_model/**/* 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
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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
|
| 36 |
+
en/MeloTTS-English-ax630c/decoder-en-au.axmodel filter=lfs diff=lfs merge=lfs -text
|
| 37 |
+
en/MeloTTS-English-ax630c/decoder-en-br.axmodel filter=lfs diff=lfs merge=lfs -text
|
| 38 |
+
en/MeloTTS-English-ax630c/decoder-en-default.axmodel filter=lfs diff=lfs merge=lfs -text
|
| 39 |
+
en/MeloTTS-English-ax630c/decoder-en-india.axmodel filter=lfs diff=lfs merge=lfs -text
|
| 40 |
+
en/MeloTTS-English-ax630c/decoder-en-us.axmodel filter=lfs diff=lfs merge=lfs -text
|
| 41 |
+
en/MeloTTS-English-ax630c/en_tn_tagger.fst filter=lfs diff=lfs merge=lfs -text
|
| 42 |
+
en/MeloTTS-English-ax630c/en_tn_verbalizer.fst filter=lfs diff=lfs merge=lfs -text
|
| 43 |
+
en/MeloTTS-English-ax630c/lexicon-en.txt filter=lfs diff=lfs merge=lfs -text
|
| 44 |
+
en/MeloTTS-English-ax650/decoder-en-au.axmodel filter=lfs diff=lfs merge=lfs -text
|
| 45 |
+
en/MeloTTS-English-ax650/decoder-en-br.axmodel filter=lfs diff=lfs merge=lfs -text
|
| 46 |
+
en/MeloTTS-English-ax650/decoder-en-default.axmodel filter=lfs diff=lfs merge=lfs -text
|
| 47 |
+
en/MeloTTS-English-ax650/decoder-en-india.axmodel filter=lfs diff=lfs merge=lfs -text
|
| 48 |
+
en/MeloTTS-English-ax650/decoder-en-us.axmodel filter=lfs diff=lfs merge=lfs -text
|
| 49 |
+
en/MeloTTS-English-ax650/en_tn_tagger.fst filter=lfs diff=lfs merge=lfs -text
|
| 50 |
+
en/MeloTTS-English-ax650/en_tn_verbalizer.fst filter=lfs diff=lfs merge=lfs -text
|
| 51 |
+
en/MeloTTS-English-ax650/lexicon-en.txt filter=lfs diff=lfs merge=lfs -text
|
| 52 |
+
es/MeloTTS-Spanish-ax630c/decoder-es-es.axmodel filter=lfs diff=lfs merge=lfs -text
|
| 53 |
+
es/MeloTTS-Spanish-ax650/decoder-es-es.axmodel filter=lfs diff=lfs merge=lfs -text
|
| 54 |
+
ja/MeloTTS-Japanese-ax630c/decoder-ja-jp.axmodel filter=lfs diff=lfs merge=lfs -text
|
| 55 |
+
ja/MeloTTS-Japanese-ax630c/ja_tn_tagger.fst filter=lfs diff=lfs merge=lfs -text
|
| 56 |
+
ja/MeloTTS-Japanese-ax650/decoder-ja-jp.axmodel filter=lfs diff=lfs merge=lfs -text
|
| 57 |
+
ja/MeloTTS-Japanese-ax650/ja_tn_tagger.fst filter=lfs diff=lfs merge=lfs -text
|
| 58 |
+
ko/MeloTTS-Korean[[:space:]](mobilint)/MeloTTS-Korean_decoder.mxq filter=lfs diff=lfs merge=lfs -text
|
| 59 |
+
ko/MeloTTS-Korean[[:space:]](mobilint)/MeloTTS-Korean_encoder.mxq filter=lfs diff=lfs merge=lfs -text
|
| 60 |
+
ko/MeloTTS-Korean-GGUF/model.gguf filter=lfs diff=lfs merge=lfs -text
|
| 61 |
+
vi/MeloTTS-Vietnamese/samples/sample-2.wav filter=lfs diff=lfs merge=lfs -text
|
| 62 |
+
vi/MeloTTS-Vietnamese/samples/sample-3.wav filter=lfs diff=lfs merge=lfs -text
|
| 63 |
+
vi/MeloTTS-Vietnamese/samples/sample.wav filter=lfs diff=lfs merge=lfs -text
|
| 64 |
+
zh,en/MeloTTS-Chinese-ax630c/decoder-zh-cn.axmodel filter=lfs diff=lfs merge=lfs -text
|
| 65 |
+
zh,en/MeloTTS-Chinese-ax630c/zh_tn_tagger.fst filter=lfs diff=lfs merge=lfs -text
|
| 66 |
+
zh,en/MeloTTS-Chinese-ax630c/zh_tn_verbalizer.fst filter=lfs diff=lfs merge=lfs -text
|
| 67 |
+
zh,en/MeloTTS-Chinese-ax650/decoder-zh-cn.axmodel filter=lfs diff=lfs merge=lfs -text
|
| 68 |
+
zh,en/MeloTTS-Chinese-ax650/zh_tn_tagger.fst filter=lfs diff=lfs merge=lfs -text
|
| 69 |
+
zh,en/MeloTTS-Chinese-ax650/zh_tn_verbalizer.fst filter=lfs diff=lfs merge=lfs -text
|
| 70 |
+
zh,en/melotts-maixcam2/melotts-maixcam2/melotts-decoder-zh.axmodel filter=lfs diff=lfs merge=lfs -text
|
| 71 |
+
zh,en/MeloTTS-RKNN2/decoder.rknn filter=lfs diff=lfs merge=lfs -text
|
| 72 |
+
zh,en/MeloTTS-RKNN2/output.wav filter=lfs diff=lfs merge=lfs -text
|
| 73 |
+
zh,en/MeloTTS-RKNN2/text/fr_phonemizer/example_ipa.txt filter=lfs diff=lfs merge=lfs -text
|
| 74 |
+
zh,en/MeloTTS.cpp/ov_models/cppinyin/cpp_pinyin.raw filter=lfs diff=lfs merge=lfs -text
|
| 75 |
+
zh,en/MeloTTS/decoder-ax630c/decoder-zh.axmodel filter=lfs diff=lfs merge=lfs -text
|
| 76 |
+
zh,en/MeloTTS/decoder-ax650/decoder-en.axmodel filter=lfs diff=lfs merge=lfs -text
|
| 77 |
+
zh,en/MeloTTS/decoder-ax650/decoder-jp.axmodel filter=lfs diff=lfs merge=lfs -text
|
| 78 |
+
zh,en/MeloTTS/decoder-ax650/decoder-zh.axmodel filter=lfs diff=lfs merge=lfs -text
|
| 79 |
+
zh,en/MeloTTS/python/text/fr_phonemizer/example_ipa.txt filter=lfs diff=lfs merge=lfs -text
|
en/MeloTTS-English-ax630c/.gitattributes
ADDED
|
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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
|
| 36 |
+
*.axmodel filter=lfs diff=lfs merge=lfs -text
|
| 37 |
+
*.txt filter=lfs diff=lfs merge=lfs -text
|
| 38 |
+
*.fst filter=lfs diff=lfs merge=lfs -text
|
en/MeloTTS-English-ax630c/README.md
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
---
|
en/MeloTTS-English-ax630c/decoder-en-au.axmodel
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:83ed6fe29fcb6c81e6c7421d350bd66cd73346253aab4d7ff2d285502157bf6f
|
| 3 |
+
size 47278788
|
en/MeloTTS-English-ax630c/decoder-en-br.axmodel
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:78a4f8f8f4820960bb5657d5f0fa209a3a02df9fd4446e7b65d126e60c93f60a
|
| 3 |
+
size 47278676
|
en/MeloTTS-English-ax630c/decoder-en-default.axmodel
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5bec45ddc5347459ed086c254cfea06254cf253f006bacf38021d1aaf10625f9
|
| 3 |
+
size 47279068
|
en/MeloTTS-English-ax630c/decoder-en-india.axmodel
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:32260c4a0fa5834b7d25f2ca50578324662491c1ca1979b845b59c505d8e1d5e
|
| 3 |
+
size 47278188
|
en/MeloTTS-English-ax630c/decoder-en-us.axmodel
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9d7fbb960e3303ff69bc2abd5fc6bcb310d92129cc6a523560c83924f67b6950
|
| 3 |
+
size 47284964
|
en/MeloTTS-English-ax630c/en_tn_tagger.fst
ADDED
|
|
Git LFS Details
|
en/MeloTTS-English-ax630c/en_tn_verbalizer.fst
ADDED
|
|
Git LFS Details
|
en/MeloTTS-English-ax630c/encoder-en.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7c5763aa36eb63e61094448307ebc44719d4d0b198cb4757491094f92c7d530c
|
| 3 |
+
size 31479747
|
en/MeloTTS-English-ax630c/g-en-au.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3fced7ec09366b10a37e70f3b2579ae11bb5acf2a6441ec4c50e87ce135b259f
|
| 3 |
+
size 1024
|
en/MeloTTS-English-ax630c/g-en-br.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6477b4b9f80d21060c2dfb3b517904051d804ee4efbc74d4dd9136e1ecf8c11a
|
| 3 |
+
size 1024
|
en/MeloTTS-English-ax630c/g-en-default.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5e4926b28ead5c25fe3b7c6496525b78ed6f4c4200706b758e9ca5dfd1600331
|
| 3 |
+
size 1024
|
en/MeloTTS-English-ax630c/g-en-india.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c720982b6ed23e4077f97267068b721b343ece2acbae2e1aa7c2b4953b337322
|
| 3 |
+
size 1024
|
en/MeloTTS-English-ax630c/g-en-us.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:094bf0dbe1cd6c9408707209b2b7261b9df2cd5917d310bfac5945a15a31821a
|
| 3 |
+
size 1024
|
en/MeloTTS-English-ax630c/lexicon-en.txt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:68eeddf2e5a2053ff3b0eb93ed4d503f3727a9d7fed0a5078728173c13cc15a3
|
| 3 |
+
size 19671122
|
en/MeloTTS-English-ax630c/source.txt
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
https://huggingface.co/M5Stack/MeloTTS-English-ax630c
|
en/MeloTTS-English-ax630c/tokens-en.txt
ADDED
|
@@ -0,0 +1,219 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
_ 0
|
| 2 |
+
" 1
|
| 3 |
+
( 2
|
| 4 |
+
) 3
|
| 5 |
+
* 4
|
| 6 |
+
/ 5
|
| 7 |
+
: 6
|
| 8 |
+
AA 7
|
| 9 |
+
E 8
|
| 10 |
+
EE 9
|
| 11 |
+
En 10
|
| 12 |
+
N 11
|
| 13 |
+
OO 12
|
| 14 |
+
Q 13
|
| 15 |
+
V 14
|
| 16 |
+
[ 15
|
| 17 |
+
\ 16
|
| 18 |
+
] 17
|
| 19 |
+
^ 18
|
| 20 |
+
a 19
|
| 21 |
+
a: 20
|
| 22 |
+
aa 21
|
| 23 |
+
ae 22
|
| 24 |
+
ah 23
|
| 25 |
+
ai 24
|
| 26 |
+
an 25
|
| 27 |
+
ang 26
|
| 28 |
+
ao 27
|
| 29 |
+
aw 28
|
| 30 |
+
ay 29
|
| 31 |
+
b 30
|
| 32 |
+
by 31
|
| 33 |
+
c 32
|
| 34 |
+
ch 33
|
| 35 |
+
d 34
|
| 36 |
+
dh 35
|
| 37 |
+
dy 36
|
| 38 |
+
e 37
|
| 39 |
+
e: 38
|
| 40 |
+
eh 39
|
| 41 |
+
ei 40
|
| 42 |
+
en 41
|
| 43 |
+
eng 42
|
| 44 |
+
er 43
|
| 45 |
+
ey 44
|
| 46 |
+
f 45
|
| 47 |
+
g 46
|
| 48 |
+
gy 47
|
| 49 |
+
h 48
|
| 50 |
+
hh 49
|
| 51 |
+
hy 50
|
| 52 |
+
i 51
|
| 53 |
+
i0 52
|
| 54 |
+
i: 53
|
| 55 |
+
ia 54
|
| 56 |
+
ian 55
|
| 57 |
+
iang 56
|
| 58 |
+
iao 57
|
| 59 |
+
ie 58
|
| 60 |
+
ih 59
|
| 61 |
+
in 60
|
| 62 |
+
ing 61
|
| 63 |
+
iong 62
|
| 64 |
+
ir 63
|
| 65 |
+
iu 64
|
| 66 |
+
iy 65
|
| 67 |
+
j 66
|
| 68 |
+
jh 67
|
| 69 |
+
k 68
|
| 70 |
+
ky 69
|
| 71 |
+
l 70
|
| 72 |
+
m 71
|
| 73 |
+
my 72
|
| 74 |
+
n 73
|
| 75 |
+
ng 74
|
| 76 |
+
ny 75
|
| 77 |
+
o 76
|
| 78 |
+
o: 77
|
| 79 |
+
ong 78
|
| 80 |
+
ou 79
|
| 81 |
+
ow 80
|
| 82 |
+
oy 81
|
| 83 |
+
p 82
|
| 84 |
+
py 83
|
| 85 |
+
q 84
|
| 86 |
+
r 85
|
| 87 |
+
ry 86
|
| 88 |
+
s 87
|
| 89 |
+
sh 88
|
| 90 |
+
t 89
|
| 91 |
+
th 90
|
| 92 |
+
ts 91
|
| 93 |
+
ty 92
|
| 94 |
+
u 93
|
| 95 |
+
u: 94
|
| 96 |
+
ua 95
|
| 97 |
+
uai 96
|
| 98 |
+
uan 97
|
| 99 |
+
uang 98
|
| 100 |
+
uh 99
|
| 101 |
+
ui 100
|
| 102 |
+
un 101
|
| 103 |
+
uo 102
|
| 104 |
+
uw 103
|
| 105 |
+
v 104
|
| 106 |
+
van 105
|
| 107 |
+
ve 106
|
| 108 |
+
vn 107
|
| 109 |
+
w 108
|
| 110 |
+
x 109
|
| 111 |
+
y 110
|
| 112 |
+
z 111
|
| 113 |
+
zh 112
|
| 114 |
+
zy 113
|
| 115 |
+
~ 114
|
| 116 |
+
¡ 115
|
| 117 |
+
¿ 116
|
| 118 |
+
æ 117
|
| 119 |
+
ç 118
|
| 120 |
+
ð 119
|
| 121 |
+
ø 120
|
| 122 |
+
ŋ 121
|
| 123 |
+
œ 122
|
| 124 |
+
ɐ 123
|
| 125 |
+
ɑ 124
|
| 126 |
+
ɒ 125
|
| 127 |
+
ɔ 126
|
| 128 |
+
ɕ 127
|
| 129 |
+
ə 128
|
| 130 |
+
ɛ 129
|
| 131 |
+
ɜ 130
|
| 132 |
+
ɡ 131
|
| 133 |
+
ɣ 132
|
| 134 |
+
ɥ 133
|
| 135 |
+
ɦ 134
|
| 136 |
+
ɪ 135
|
| 137 |
+
ɫ 136
|
| 138 |
+
ɬ 137
|
| 139 |
+
ɭ 138
|
| 140 |
+
ɯ 139
|
| 141 |
+
ɲ 140
|
| 142 |
+
ɵ 141
|
| 143 |
+
ɸ 142
|
| 144 |
+
ɹ 143
|
| 145 |
+
ɾ 144
|
| 146 |
+
ʁ 145
|
| 147 |
+
ʃ 146
|
| 148 |
+
ʊ 147
|
| 149 |
+
ʌ 148
|
| 150 |
+
ʎ 149
|
| 151 |
+
ʏ 150
|
| 152 |
+
ʑ 151
|
| 153 |
+
ʒ 152
|
| 154 |
+
ʝ 153
|
| 155 |
+
ʲ 154
|
| 156 |
+
ˈ 155
|
| 157 |
+
ˌ 156
|
| 158 |
+
ː 157
|
| 159 |
+
̃ 158
|
| 160 |
+
̩ 159
|
| 161 |
+
β 160
|
| 162 |
+
θ 161
|
| 163 |
+
ᄀ 162
|
| 164 |
+
ᄁ 163
|
| 165 |
+
ᄂ 164
|
| 166 |
+
ᄃ 165
|
| 167 |
+
ᄄ 166
|
| 168 |
+
ᄅ 167
|
| 169 |
+
ᄆ 168
|
| 170 |
+
ᄇ 169
|
| 171 |
+
ᄈ 170
|
| 172 |
+
ᄉ 171
|
| 173 |
+
ᄊ 172
|
| 174 |
+
ᄋ 173
|
| 175 |
+
ᄌ 174
|
| 176 |
+
ᄍ 175
|
| 177 |
+
ᄎ 176
|
| 178 |
+
ᄏ 177
|
| 179 |
+
ᄐ 178
|
| 180 |
+
ᄑ 179
|
| 181 |
+
ᄒ 180
|
| 182 |
+
ᅡ 181
|
| 183 |
+
ᅢ 182
|
| 184 |
+
ᅣ 183
|
| 185 |
+
ᅤ 184
|
| 186 |
+
ᅥ 185
|
| 187 |
+
ᅦ 186
|
| 188 |
+
ᅧ 187
|
| 189 |
+
ᅨ 188
|
| 190 |
+
ᅩ 189
|
| 191 |
+
ᅪ 190
|
| 192 |
+
ᅫ 191
|
| 193 |
+
ᅬ 192
|
| 194 |
+
ᅭ 193
|
| 195 |
+
ᅮ 194
|
| 196 |
+
ᅯ 195
|
| 197 |
+
ᅰ 196
|
| 198 |
+
ᅱ 197
|
| 199 |
+
ᅲ 198
|
| 200 |
+
ᅳ 199
|
| 201 |
+
ᅴ 200
|
| 202 |
+
ᅵ 201
|
| 203 |
+
ᆨ 202
|
| 204 |
+
ᆫ 203
|
| 205 |
+
ᆮ 204
|
| 206 |
+
ᆯ 205
|
| 207 |
+
ᆷ 206
|
| 208 |
+
ᆸ 207
|
| 209 |
+
ᆼ 208
|
| 210 |
+
ㄸ 209
|
| 211 |
+
! 210
|
| 212 |
+
? 211
|
| 213 |
+
… 212
|
| 214 |
+
, 213
|
| 215 |
+
. 214
|
| 216 |
+
' 215
|
| 217 |
+
- 216
|
| 218 |
+
SP 217
|
| 219 |
+
UNK 218
|
en/MeloTTS-English-ax650/.gitattributes
ADDED
|
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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
|
| 36 |
+
*.axmodel filter=lfs diff=lfs merge=lfs -text
|
| 37 |
+
*.txt filter=lfs diff=lfs merge=lfs -text
|
| 38 |
+
*.fst filter=lfs diff=lfs merge=lfs -text
|
en/MeloTTS-English-ax650/README.md
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
---
|
en/MeloTTS-English-ax650/decoder-en-au.axmodel
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:47ab8f57794753e056b7a2aebbbf0227a3861390aa90feb817993f216c26ba97
|
| 3 |
+
size 44845204
|
en/MeloTTS-English-ax650/decoder-en-br.axmodel
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6fda11797c46f210ccba8470147961944026710e9df2e1eae7f8715be3f017a9
|
| 3 |
+
size 44845366
|
en/MeloTTS-English-ax650/decoder-en-default.axmodel
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:79f7440a00c8340ae68e01daa3ca17dac2d4309d0b7e82732f293df00367cd45
|
| 3 |
+
size 44845914
|
en/MeloTTS-English-ax650/decoder-en-india.axmodel
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:da3bf0273ae8728513cafbe27998a9ba2b4fc458d695f9c90e1216b00f6703b7
|
| 3 |
+
size 44846966
|
en/MeloTTS-English-ax650/decoder-en-us.axmodel
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7c4c114f4a461a2e4304c6d61e55ddc95bb4a27ead352216213b72ad798acbff
|
| 3 |
+
size 44846264
|
en/MeloTTS-English-ax650/en_tn_tagger.fst
ADDED
|
|
Git LFS Details
|
en/MeloTTS-English-ax650/en_tn_verbalizer.fst
ADDED
|
|
Git LFS Details
|
en/MeloTTS-English-ax650/encoder-en.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7c5763aa36eb63e61094448307ebc44719d4d0b198cb4757491094f92c7d530c
|
| 3 |
+
size 31479747
|
en/MeloTTS-English-ax650/g-en-au.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3fced7ec09366b10a37e70f3b2579ae11bb5acf2a6441ec4c50e87ce135b259f
|
| 3 |
+
size 1024
|
en/MeloTTS-English-ax650/g-en-br.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6477b4b9f80d21060c2dfb3b517904051d804ee4efbc74d4dd9136e1ecf8c11a
|
| 3 |
+
size 1024
|
en/MeloTTS-English-ax650/g-en-default.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5e4926b28ead5c25fe3b7c6496525b78ed6f4c4200706b758e9ca5dfd1600331
|
| 3 |
+
size 1024
|
en/MeloTTS-English-ax650/g-en-india.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c720982b6ed23e4077f97267068b721b343ece2acbae2e1aa7c2b4953b337322
|
| 3 |
+
size 1024
|
en/MeloTTS-English-ax650/g-en-us.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:094bf0dbe1cd6c9408707209b2b7261b9df2cd5917d310bfac5945a15a31821a
|
| 3 |
+
size 1024
|
en/MeloTTS-English-ax650/lexicon-en.txt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:68eeddf2e5a2053ff3b0eb93ed4d503f3727a9d7fed0a5078728173c13cc15a3
|
| 3 |
+
size 19671122
|
en/MeloTTS-English-ax650/source.txt
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
https://huggingface.co/M5Stack/MeloTTS-English-ax650
|
en/MeloTTS-English-ax650/tokens-en.txt
ADDED
|
@@ -0,0 +1,219 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
_ 0
|
| 2 |
+
" 1
|
| 3 |
+
( 2
|
| 4 |
+
) 3
|
| 5 |
+
* 4
|
| 6 |
+
/ 5
|
| 7 |
+
: 6
|
| 8 |
+
AA 7
|
| 9 |
+
E 8
|
| 10 |
+
EE 9
|
| 11 |
+
En 10
|
| 12 |
+
N 11
|
| 13 |
+
OO 12
|
| 14 |
+
Q 13
|
| 15 |
+
V 14
|
| 16 |
+
[ 15
|
| 17 |
+
\ 16
|
| 18 |
+
] 17
|
| 19 |
+
^ 18
|
| 20 |
+
a 19
|
| 21 |
+
a: 20
|
| 22 |
+
aa 21
|
| 23 |
+
ae 22
|
| 24 |
+
ah 23
|
| 25 |
+
ai 24
|
| 26 |
+
an 25
|
| 27 |
+
ang 26
|
| 28 |
+
ao 27
|
| 29 |
+
aw 28
|
| 30 |
+
ay 29
|
| 31 |
+
b 30
|
| 32 |
+
by 31
|
| 33 |
+
c 32
|
| 34 |
+
ch 33
|
| 35 |
+
d 34
|
| 36 |
+
dh 35
|
| 37 |
+
dy 36
|
| 38 |
+
e 37
|
| 39 |
+
e: 38
|
| 40 |
+
eh 39
|
| 41 |
+
ei 40
|
| 42 |
+
en 41
|
| 43 |
+
eng 42
|
| 44 |
+
er 43
|
| 45 |
+
ey 44
|
| 46 |
+
f 45
|
| 47 |
+
g 46
|
| 48 |
+
gy 47
|
| 49 |
+
h 48
|
| 50 |
+
hh 49
|
| 51 |
+
hy 50
|
| 52 |
+
i 51
|
| 53 |
+
i0 52
|
| 54 |
+
i: 53
|
| 55 |
+
ia 54
|
| 56 |
+
ian 55
|
| 57 |
+
iang 56
|
| 58 |
+
iao 57
|
| 59 |
+
ie 58
|
| 60 |
+
ih 59
|
| 61 |
+
in 60
|
| 62 |
+
ing 61
|
| 63 |
+
iong 62
|
| 64 |
+
ir 63
|
| 65 |
+
iu 64
|
| 66 |
+
iy 65
|
| 67 |
+
j 66
|
| 68 |
+
jh 67
|
| 69 |
+
k 68
|
| 70 |
+
ky 69
|
| 71 |
+
l 70
|
| 72 |
+
m 71
|
| 73 |
+
my 72
|
| 74 |
+
n 73
|
| 75 |
+
ng 74
|
| 76 |
+
ny 75
|
| 77 |
+
o 76
|
| 78 |
+
o: 77
|
| 79 |
+
ong 78
|
| 80 |
+
ou 79
|
| 81 |
+
ow 80
|
| 82 |
+
oy 81
|
| 83 |
+
p 82
|
| 84 |
+
py 83
|
| 85 |
+
q 84
|
| 86 |
+
r 85
|
| 87 |
+
ry 86
|
| 88 |
+
s 87
|
| 89 |
+
sh 88
|
| 90 |
+
t 89
|
| 91 |
+
th 90
|
| 92 |
+
ts 91
|
| 93 |
+
ty 92
|
| 94 |
+
u 93
|
| 95 |
+
u: 94
|
| 96 |
+
ua 95
|
| 97 |
+
uai 96
|
| 98 |
+
uan 97
|
| 99 |
+
uang 98
|
| 100 |
+
uh 99
|
| 101 |
+
ui 100
|
| 102 |
+
un 101
|
| 103 |
+
uo 102
|
| 104 |
+
uw 103
|
| 105 |
+
v 104
|
| 106 |
+
van 105
|
| 107 |
+
ve 106
|
| 108 |
+
vn 107
|
| 109 |
+
w 108
|
| 110 |
+
x 109
|
| 111 |
+
y 110
|
| 112 |
+
z 111
|
| 113 |
+
zh 112
|
| 114 |
+
zy 113
|
| 115 |
+
~ 114
|
| 116 |
+
¡ 115
|
| 117 |
+
¿ 116
|
| 118 |
+
æ 117
|
| 119 |
+
ç 118
|
| 120 |
+
ð 119
|
| 121 |
+
ø 120
|
| 122 |
+
ŋ 121
|
| 123 |
+
œ 122
|
| 124 |
+
ɐ 123
|
| 125 |
+
ɑ 124
|
| 126 |
+
ɒ 125
|
| 127 |
+
ɔ 126
|
| 128 |
+
ɕ 127
|
| 129 |
+
ə 128
|
| 130 |
+
ɛ 129
|
| 131 |
+
ɜ 130
|
| 132 |
+
ɡ 131
|
| 133 |
+
ɣ 132
|
| 134 |
+
ɥ 133
|
| 135 |
+
ɦ 134
|
| 136 |
+
ɪ 135
|
| 137 |
+
ɫ 136
|
| 138 |
+
ɬ 137
|
| 139 |
+
ɭ 138
|
| 140 |
+
ɯ 139
|
| 141 |
+
ɲ 140
|
| 142 |
+
ɵ 141
|
| 143 |
+
ɸ 142
|
| 144 |
+
ɹ 143
|
| 145 |
+
ɾ 144
|
| 146 |
+
ʁ 145
|
| 147 |
+
ʃ 146
|
| 148 |
+
ʊ 147
|
| 149 |
+
ʌ 148
|
| 150 |
+
ʎ 149
|
| 151 |
+
ʏ 150
|
| 152 |
+
ʑ 151
|
| 153 |
+
ʒ 152
|
| 154 |
+
ʝ 153
|
| 155 |
+
ʲ 154
|
| 156 |
+
ˈ 155
|
| 157 |
+
ˌ 156
|
| 158 |
+
ː 157
|
| 159 |
+
̃ 158
|
| 160 |
+
̩ 159
|
| 161 |
+
β 160
|
| 162 |
+
θ 161
|
| 163 |
+
ᄀ 162
|
| 164 |
+
ᄁ 163
|
| 165 |
+
ᄂ 164
|
| 166 |
+
ᄃ 165
|
| 167 |
+
ᄄ 166
|
| 168 |
+
ᄅ 167
|
| 169 |
+
ᄆ 168
|
| 170 |
+
ᄇ 169
|
| 171 |
+
ᄈ 170
|
| 172 |
+
ᄉ 171
|
| 173 |
+
ᄊ 172
|
| 174 |
+
ᄋ 173
|
| 175 |
+
ᄌ 174
|
| 176 |
+
ᄍ 175
|
| 177 |
+
ᄎ 176
|
| 178 |
+
ᄏ 177
|
| 179 |
+
ᄐ 178
|
| 180 |
+
ᄑ 179
|
| 181 |
+
ᄒ 180
|
| 182 |
+
ᅡ 181
|
| 183 |
+
ᅢ 182
|
| 184 |
+
ᅣ 183
|
| 185 |
+
ᅤ 184
|
| 186 |
+
ᅥ 185
|
| 187 |
+
ᅦ 186
|
| 188 |
+
ᅧ 187
|
| 189 |
+
ᅨ 188
|
| 190 |
+
ᅩ 189
|
| 191 |
+
ᅪ 190
|
| 192 |
+
ᅫ 191
|
| 193 |
+
ᅬ 192
|
| 194 |
+
ᅭ 193
|
| 195 |
+
ᅮ 194
|
| 196 |
+
ᅯ 195
|
| 197 |
+
ᅰ 196
|
| 198 |
+
ᅱ 197
|
| 199 |
+
ᅲ 198
|
| 200 |
+
ᅳ 199
|
| 201 |
+
ᅴ 200
|
| 202 |
+
ᅵ 201
|
| 203 |
+
ᆨ 202
|
| 204 |
+
ᆫ 203
|
| 205 |
+
ᆮ 204
|
| 206 |
+
ᆯ 205
|
| 207 |
+
ᆷ 206
|
| 208 |
+
ᆸ 207
|
| 209 |
+
ᆼ 208
|
| 210 |
+
ㄸ 209
|
| 211 |
+
! 210
|
| 212 |
+
? 211
|
| 213 |
+
… 212
|
| 214 |
+
, 213
|
| 215 |
+
. 214
|
| 216 |
+
' 215
|
| 217 |
+
- 216
|
| 218 |
+
SP 217
|
| 219 |
+
UNK 218
|
en/MeloTTS-English-v2/.gitattributes
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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
|
en/MeloTTS-English-v2/README.md
ADDED
|
@@ -0,0 +1,103 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
language:
|
| 4 |
+
- ko
|
| 5 |
+
pipeline_tag: text-to-speech
|
| 6 |
+
---
|
| 7 |
+
|
| 8 |
+
# MeloTTS
|
| 9 |
+
|
| 10 |
+
MeloTTS is a **high-quality multi-lingual** text-to-speech library by [MyShell.ai](https://myshell.ai). Supported languages include:
|
| 11 |
+
|
| 12 |
+
|
| 13 |
+
| Model card | Example |
|
| 14 |
+
| --- | --- |
|
| 15 |
+
| [English](https://huggingface.co/myshell-ai/MeloTTS-English-v2) (American) | [Link](https://myshell-public-repo-hosting.s3.amazonaws.com/myshellttsbase/examples/en/EN-US/speed_1.0/sent_000.wav) |
|
| 16 |
+
| [English](https://huggingface.co/myshell-ai/MeloTTS-English-v2) (British) | [Link](https://myshell-public-repo-hosting.s3.amazonaws.com/myshellttsbase/examples/en/EN-BR/speed_1.0/sent_000.wav) |
|
| 17 |
+
| [English](https://huggingface.co/myshell-ai/MeloTTS-English-v2) (Indian) | [Link](https://myshell-public-repo-hosting.s3.amazonaws.com/myshellttsbase/examples/en/EN_INDIA/speed_1.0/sent_000.wav) |
|
| 18 |
+
| [English](https://huggingface.co/myshell-ai/MeloTTS-English-v2) (Australian) | [Link](https://myshell-public-repo-hosting.s3.amazonaws.com/myshellttsbase/examples/en/EN-AU/speed_1.0/sent_000.wav) |
|
| 19 |
+
| [English](https://huggingface.co/myshell-ai/MeloTTS-English-v2) (Default) | [Link](https://myshell-public-repo-hosting.s3.amazonaws.com/myshellttsbase/examples/en/EN-Default/speed_1.0/sent_000.wav) |
|
| 20 |
+
| [Spanish](https://huggingface.co/myshell-ai/MeloTTS-Spanish) | [Link](https://myshell-public-repo-hosting.s3.amazonaws.com/myshellttsbase/examples/es/ES/speed_1.0/sent_000.wav) |
|
| 21 |
+
| [French](https://huggingface.co/myshell-ai/MeloTTS-French) | [Link](https://myshell-public-repo-hosting.s3.amazonaws.com/myshellttsbase/examples/fr/FR/speed_1.0/sent_000.wav) |
|
| 22 |
+
| [Chinese](https://huggingface.co/myshell-ai/MeloTTS-Chinese) (mix EN) | [Link](https://myshell-public-repo-hosting.s3.amazonaws.com/myshellttsbase/examples/zh/ZH/speed_1.0/sent_008.wav) |
|
| 23 |
+
| [Japanese](https://huggingface.co/myshell-ai/MeloTTS-Japanese) | [Link](https://myshell-public-repo-hosting.s3.amazonaws.com/myshellttsbase/examples/jp/JP/speed_1.0/sent_000.wav) |
|
| 24 |
+
| [Korean](https://huggingface.co/myshell-ai/MeloTTS-Korean/) | [Link](https://myshell-public-repo-hosting.s3.amazonaws.com/myshellttsbase/examples/kr/KR/speed_1.0/sent_000.wav) |
|
| 25 |
+
|
| 26 |
+
Some other features include:
|
| 27 |
+
- The Chinese speaker supports `mixed Chinese and English`.
|
| 28 |
+
- Fast enough for `CPU real-time inference`.
|
| 29 |
+
|
| 30 |
+
|
| 31 |
+
## Usage
|
| 32 |
+
|
| 33 |
+
### Without Installation
|
| 34 |
+
|
| 35 |
+
An unofficial [live demo](https://huggingface.co/spaces/mrfakename/MeloTTS) is hosted on Hugging Face Spaces.
|
| 36 |
+
|
| 37 |
+
#### Use it on MyShell
|
| 38 |
+
|
| 39 |
+
There are hundreds of TTS models on MyShell, much more than MeloTTS. See examples [here](https://github.com/myshell-ai/MeloTTS/blob/main/docs/quick_use.md#use-melotts-without-installation).
|
| 40 |
+
More can be found at the widget center of [MyShell.ai](https://app.myshell.ai/robot-workshop).
|
| 41 |
+
|
| 42 |
+
### Install and Use Locally
|
| 43 |
+
|
| 44 |
+
Follow the installation steps [here](https://github.com/myshell-ai/MeloTTS/blob/main/docs/install.md#linux-and-macos-install) before using the following snippet:
|
| 45 |
+
|
| 46 |
+
```python
|
| 47 |
+
from melo.api import TTS
|
| 48 |
+
|
| 49 |
+
# Speed is adjustable
|
| 50 |
+
speed = 1.0
|
| 51 |
+
|
| 52 |
+
# CPU is sufficient for real-time inference.
|
| 53 |
+
# You can set it manually to 'cpu' or 'cuda' or 'cuda:0' or 'mps'
|
| 54 |
+
device = 'auto' # Will automatically use GPU if available
|
| 55 |
+
|
| 56 |
+
# English
|
| 57 |
+
text = "Did you ever hear a folk tale about a giant turtle?"
|
| 58 |
+
model = TTS(language='EN_V2', device=device)
|
| 59 |
+
speaker_ids = model.hps.data.spk2id
|
| 60 |
+
|
| 61 |
+
# American accent
|
| 62 |
+
output_path = 'en-us.wav'
|
| 63 |
+
model.tts_to_file(text, speaker_ids['EN-US'], output_path, speed=speed)
|
| 64 |
+
|
| 65 |
+
# British accent
|
| 66 |
+
output_path = 'en-br.wav'
|
| 67 |
+
model.tts_to_file(text, speaker_ids['EN-BR'], output_path, speed=speed)
|
| 68 |
+
|
| 69 |
+
# Indian accent
|
| 70 |
+
output_path = 'en-india.wav'
|
| 71 |
+
model.tts_to_file(text, speaker_ids['EN_INDIA'], output_path, speed=speed)
|
| 72 |
+
|
| 73 |
+
# Australian accent
|
| 74 |
+
output_path = 'en-au.wav'
|
| 75 |
+
model.tts_to_file(text, speaker_ids['EN-AU'], output_path, speed=speed)
|
| 76 |
+
|
| 77 |
+
# Default accent
|
| 78 |
+
output_path = 'en-default.wav'
|
| 79 |
+
model.tts_to_file(text, speaker_ids['EN-Default'], output_path, speed=speed)
|
| 80 |
+
|
| 81 |
+
```
|
| 82 |
+
|
| 83 |
+
|
| 84 |
+
## Join the Community
|
| 85 |
+
|
| 86 |
+
**Open Source AI Grant**
|
| 87 |
+
|
| 88 |
+
We are actively sponsoring open-source AI projects. The sponsorship includes GPU resources, fundings and intellectual support (collaboration with top research labs). We welcome both reseach and engineering projects, as long as the open-source community needs them. Please contact [Zengyi Qin](https://www.qinzy.tech/) if you are interested.
|
| 89 |
+
|
| 90 |
+
**Contributing**
|
| 91 |
+
|
| 92 |
+
If you find this work useful, please consider contributing to the GitHub [repo](https://github.com/myshell-ai/MeloTTS).
|
| 93 |
+
|
| 94 |
+
- Many thanks to [@fakerybakery](https://github.com/fakerybakery) for adding the Web UI and CLI part.
|
| 95 |
+
|
| 96 |
+
## License
|
| 97 |
+
|
| 98 |
+
This library is under MIT License, which means it is free for both commercial and non-commercial use.
|
| 99 |
+
|
| 100 |
+
## Acknowledgements
|
| 101 |
+
|
| 102 |
+
This implementation is based on [TTS](https://github.com/coqui-ai/TTS), [VITS](https://github.com/jaywalnut310/vits), [VITS2](https://github.com/daniilrobnikov/vits2) and [Bert-VITS2](https://github.com/fishaudio/Bert-VITS2). We appreciate their awesome work.
|
| 103 |
+
|
en/MeloTTS-English-v2/checkpoint.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:794226eb7c1745f3ca281b290613d5f39aa5b0d3b16a117009966f4aaf184757
|
| 3 |
+
size 207769356
|
en/MeloTTS-English-v2/config.json
ADDED
|
@@ -0,0 +1,189 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"train": {
|
| 3 |
+
"segment_size": 16384
|
| 4 |
+
},
|
| 5 |
+
"data": {
|
| 6 |
+
"sampling_rate": 44100,
|
| 7 |
+
"filter_length": 2048,
|
| 8 |
+
"hop_length": 512,
|
| 9 |
+
"add_blank": true,
|
| 10 |
+
"n_speakers": 256,
|
| 11 |
+
"spk2id": {
|
| 12 |
+
"EN-US": 0,
|
| 13 |
+
"EN-BR": 1,
|
| 14 |
+
"EN-INDIA": 2,
|
| 15 |
+
"EN-AU": 4
|
| 16 |
+
}
|
| 17 |
+
},
|
| 18 |
+
"model": {
|
| 19 |
+
"use_spk_conditioned_encoder": true,
|
| 20 |
+
"use_noise_scaled_mas": true,
|
| 21 |
+
"use_mel_posterior_encoder": false,
|
| 22 |
+
"use_duration_discriminator": true,
|
| 23 |
+
"inter_channels": 192,
|
| 24 |
+
"hidden_channels": 192,
|
| 25 |
+
"filter_channels": 768,
|
| 26 |
+
"n_heads": 2,
|
| 27 |
+
"n_layers": 6,
|
| 28 |
+
"n_layers_trans_flow": 3,
|
| 29 |
+
"kernel_size": 3,
|
| 30 |
+
"p_dropout": 0.1,
|
| 31 |
+
"resblock": "1",
|
| 32 |
+
"resblock_kernel_sizes": [
|
| 33 |
+
3,
|
| 34 |
+
7,
|
| 35 |
+
11
|
| 36 |
+
],
|
| 37 |
+
"resblock_dilation_sizes": [
|
| 38 |
+
[
|
| 39 |
+
1,
|
| 40 |
+
3,
|
| 41 |
+
5
|
| 42 |
+
],
|
| 43 |
+
[
|
| 44 |
+
1,
|
| 45 |
+
3,
|
| 46 |
+
5
|
| 47 |
+
],
|
| 48 |
+
[
|
| 49 |
+
1,
|
| 50 |
+
3,
|
| 51 |
+
5
|
| 52 |
+
]
|
| 53 |
+
],
|
| 54 |
+
"upsample_rates": [
|
| 55 |
+
8,
|
| 56 |
+
8,
|
| 57 |
+
2,
|
| 58 |
+
2,
|
| 59 |
+
2
|
| 60 |
+
],
|
| 61 |
+
"upsample_initial_channel": 512,
|
| 62 |
+
"upsample_kernel_sizes": [
|
| 63 |
+
16,
|
| 64 |
+
16,
|
| 65 |
+
8,
|
| 66 |
+
2,
|
| 67 |
+
2
|
| 68 |
+
],
|
| 69 |
+
"n_layers_q": 3,
|
| 70 |
+
"use_spectral_norm": false,
|
| 71 |
+
"gin_channels": 256
|
| 72 |
+
},
|
| 73 |
+
"symbols": [
|
| 74 |
+
"_",
|
| 75 |
+
"AA",
|
| 76 |
+
"E",
|
| 77 |
+
"EE",
|
| 78 |
+
"En",
|
| 79 |
+
"N",
|
| 80 |
+
"OO",
|
| 81 |
+
"V",
|
| 82 |
+
"a",
|
| 83 |
+
"a:",
|
| 84 |
+
"aa",
|
| 85 |
+
"ae",
|
| 86 |
+
"ah",
|
| 87 |
+
"ai",
|
| 88 |
+
"an",
|
| 89 |
+
"ang",
|
| 90 |
+
"ao",
|
| 91 |
+
"aw",
|
| 92 |
+
"ay",
|
| 93 |
+
"b",
|
| 94 |
+
"by",
|
| 95 |
+
"c",
|
| 96 |
+
"ch",
|
| 97 |
+
"d",
|
| 98 |
+
"dh",
|
| 99 |
+
"dy",
|
| 100 |
+
"e",
|
| 101 |
+
"e:",
|
| 102 |
+
"eh",
|
| 103 |
+
"ei",
|
| 104 |
+
"en",
|
| 105 |
+
"eng",
|
| 106 |
+
"er",
|
| 107 |
+
"ey",
|
| 108 |
+
"f",
|
| 109 |
+
"g",
|
| 110 |
+
"gy",
|
| 111 |
+
"h",
|
| 112 |
+
"hh",
|
| 113 |
+
"hy",
|
| 114 |
+
"i",
|
| 115 |
+
"i0",
|
| 116 |
+
"i:",
|
| 117 |
+
"ia",
|
| 118 |
+
"ian",
|
| 119 |
+
"iang",
|
| 120 |
+
"iao",
|
| 121 |
+
"ie",
|
| 122 |
+
"ih",
|
| 123 |
+
"in",
|
| 124 |
+
"ing",
|
| 125 |
+
"iong",
|
| 126 |
+
"ir",
|
| 127 |
+
"iu",
|
| 128 |
+
"iy",
|
| 129 |
+
"j",
|
| 130 |
+
"jh",
|
| 131 |
+
"k",
|
| 132 |
+
"ky",
|
| 133 |
+
"l",
|
| 134 |
+
"m",
|
| 135 |
+
"my",
|
| 136 |
+
"n",
|
| 137 |
+
"ng",
|
| 138 |
+
"ny",
|
| 139 |
+
"o",
|
| 140 |
+
"o:",
|
| 141 |
+
"ong",
|
| 142 |
+
"ou",
|
| 143 |
+
"ow",
|
| 144 |
+
"oy",
|
| 145 |
+
"p",
|
| 146 |
+
"py",
|
| 147 |
+
"q",
|
| 148 |
+
"r",
|
| 149 |
+
"ry",
|
| 150 |
+
"s",
|
| 151 |
+
"sh",
|
| 152 |
+
"t",
|
| 153 |
+
"th",
|
| 154 |
+
"ts",
|
| 155 |
+
"ty",
|
| 156 |
+
"u",
|
| 157 |
+
"u:",
|
| 158 |
+
"ua",
|
| 159 |
+
"uai",
|
| 160 |
+
"uan",
|
| 161 |
+
"uang",
|
| 162 |
+
"uh",
|
| 163 |
+
"ui",
|
| 164 |
+
"un",
|
| 165 |
+
"uo",
|
| 166 |
+
"uw",
|
| 167 |
+
"v",
|
| 168 |
+
"van",
|
| 169 |
+
"ve",
|
| 170 |
+
"vn",
|
| 171 |
+
"w",
|
| 172 |
+
"x",
|
| 173 |
+
"y",
|
| 174 |
+
"z",
|
| 175 |
+
"zh",
|
| 176 |
+
"zy",
|
| 177 |
+
"!",
|
| 178 |
+
"?",
|
| 179 |
+
"…",
|
| 180 |
+
",",
|
| 181 |
+
".",
|
| 182 |
+
"'",
|
| 183 |
+
"-",
|
| 184 |
+
"SP",
|
| 185 |
+
"UNK"
|
| 186 |
+
],
|
| 187 |
+
"num_tones": 11,
|
| 188 |
+
"num_languages": 3
|
| 189 |
+
}
|
en/MeloTTS-English-v2/source.txt
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
https://huggingface.co/myshell-ai/MeloTTS-English-v2
|
en/MeloTTS-English-v3/.gitattributes
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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
|
en/MeloTTS-English-v3/README.md
ADDED
|
@@ -0,0 +1,83 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
---
|
| 4 |
+
|
| 5 |
+
# MeloTTS
|
| 6 |
+
|
| 7 |
+
MeloTTS is a **high-quality multi-lingual** text-to-speech library by [MyShell.ai](https://myshell.ai). Supported languages include:
|
| 8 |
+
|
| 9 |
+
|
| 10 |
+
| Model card | Example |
|
| 11 |
+
| --- | --- |
|
| 12 |
+
| [English](https://huggingface.co/myshell-ai/MeloTTS-English-v2) (American) | [Link](https://myshell-public-repo-hosting.s3.amazonaws.com/myshellttsbase/examples/en/EN-US/speed_1.0/sent_000.wav) |
|
| 13 |
+
| [English](https://huggingface.co/myshell-ai/MeloTTS-English-v2) (British) | [Link](https://myshell-public-repo-hosting.s3.amazonaws.com/myshellttsbase/examples/en/EN-BR/speed_1.0/sent_000.wav) |
|
| 14 |
+
| [English](https://huggingface.co/myshell-ai/MeloTTS-English-v2) (Indian) | [Link](https://myshell-public-repo-hosting.s3.amazonaws.com/myshellttsbase/examples/en/EN_INDIA/speed_1.0/sent_000.wav) |
|
| 15 |
+
| [English](https://huggingface.co/myshell-ai/MeloTTS-English-v2) (Australian) | [Link](https://myshell-public-repo-hosting.s3.amazonaws.com/myshellttsbase/examples/en/EN-AU/speed_1.0/sent_000.wav) |
|
| 16 |
+
| [English](https://huggingface.co/myshell-ai/MeloTTS-English-v2) (Default) | [Link](https://myshell-public-repo-hosting.s3.amazonaws.com/myshellttsbase/examples/en/EN-Default/speed_1.0/sent_000.wav) |
|
| 17 |
+
| [Spanish](https://huggingface.co/myshell-ai/MeloTTS-Spanish) | [Link](https://myshell-public-repo-hosting.s3.amazonaws.com/myshellttsbase/examples/es/ES/speed_1.0/sent_000.wav) |
|
| 18 |
+
| [French](https://huggingface.co/myshell-ai/MeloTTS-French) | [Link](https://myshell-public-repo-hosting.s3.amazonaws.com/myshellttsbase/examples/fr/FR/speed_1.0/sent_000.wav) |
|
| 19 |
+
| [Chinese](https://huggingface.co/myshell-ai/MeloTTS-Chinese) (mix EN) | [Link](https://myshell-public-repo-hosting.s3.amazonaws.com/myshellttsbase/examples/zh/ZH/speed_1.0/sent_008.wav) |
|
| 20 |
+
| [Japanese](https://huggingface.co/myshell-ai/MeloTTS-Japanese) | [Link](https://myshell-public-repo-hosting.s3.amazonaws.com/myshellttsbase/examples/jp/JP/speed_1.0/sent_000.wav) |
|
| 21 |
+
| [Korean](https://huggingface.co/myshell-ai/MeloTTS-Korean/) | [Link](https://myshell-public-repo-hosting.s3.amazonaws.com/myshellttsbase/examples/kr/KR/speed_1.0/sent_000.wav) |
|
| 22 |
+
|
| 23 |
+
Some other features include:
|
| 24 |
+
- The Chinese speaker supports `mixed Chinese and English`.
|
| 25 |
+
- Fast enough for `CPU real-time inference`.
|
| 26 |
+
|
| 27 |
+
|
| 28 |
+
## Usage
|
| 29 |
+
|
| 30 |
+
### Without Installation
|
| 31 |
+
|
| 32 |
+
An unofficial [live demo](https://huggingface.co/spaces/mrfakename/MeloTTS) is hosted on Hugging Face Spaces.
|
| 33 |
+
|
| 34 |
+
#### Use it on MyShell
|
| 35 |
+
|
| 36 |
+
There are hundreds of TTS models on MyShell, much more than MeloTTS. See examples [here](https://github.com/myshell-ai/MeloTTS/blob/main/docs/quick_use.md#use-melotts-without-installation).
|
| 37 |
+
More can be found at the widget center of [MyShell.ai](https://app.myshell.ai/robot-workshop).
|
| 38 |
+
|
| 39 |
+
### Install and Use Locally
|
| 40 |
+
|
| 41 |
+
Follow the installation steps [here](https://github.com/myshell-ai/MeloTTS/blob/main/docs/install.md#linux-and-macos-install) before using the following snippet:
|
| 42 |
+
|
| 43 |
+
```python
|
| 44 |
+
from melo.api import TTS
|
| 45 |
+
|
| 46 |
+
# Speed is adjustable
|
| 47 |
+
speed = 1.0
|
| 48 |
+
|
| 49 |
+
# CPU is sufficient for real-time inference.
|
| 50 |
+
# You can set it manually to 'cpu' or 'cuda' or 'cuda:0' or 'mps'
|
| 51 |
+
device = 'auto' # Will automatically use GPU if available
|
| 52 |
+
|
| 53 |
+
# English
|
| 54 |
+
text = "Did you ever hear a folk tale about a giant turtle?"
|
| 55 |
+
model = TTS(language='EN_NEWEST', device=device)
|
| 56 |
+
speaker_ids = model.hps.data.spk2id
|
| 57 |
+
|
| 58 |
+
output_path = 'en-newest.wav'
|
| 59 |
+
model.tts_to_file(text, speaker_ids['EN-Newest'], output_path, speed=speed)
|
| 60 |
+
|
| 61 |
+
```
|
| 62 |
+
|
| 63 |
+
|
| 64 |
+
## Join the Community
|
| 65 |
+
|
| 66 |
+
**Open Source AI Grant**
|
| 67 |
+
|
| 68 |
+
We are actively sponsoring open-source AI projects. The sponsorship includes GPU resources, fundings and intellectual support (collaboration with top research labs). We welcome both reseach and engineering projects, as long as the open-source community needs them. Please contact [Zengyi Qin](https://www.qinzy.tech/) if you are interested.
|
| 69 |
+
|
| 70 |
+
**Contributing**
|
| 71 |
+
|
| 72 |
+
If you find this work useful, please consider contributing to the GitHub [repo](https://github.com/myshell-ai/MeloTTS).
|
| 73 |
+
|
| 74 |
+
- Many thanks to [@fakerybakery](https://github.com/fakerybakery) for adding the Web UI and CLI part.
|
| 75 |
+
|
| 76 |
+
## License
|
| 77 |
+
|
| 78 |
+
This library is under MIT License, which means it is free for both commercial and non-commercial use.
|
| 79 |
+
|
| 80 |
+
## Acknowledgements
|
| 81 |
+
|
| 82 |
+
This implementation is based on [TTS](https://github.com/coqui-ai/TTS), [VITS](https://github.com/jaywalnut310/vits), [VITS2](https://github.com/daniilrobnikov/vits2) and [Bert-VITS2](https://github.com/fishaudio/Bert-VITS2). We appreciate their awesome work.
|
| 83 |
+
|
en/MeloTTS-English-v3/checkpoint.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:959433dc1c6df618922560b4b7bc8c7af0a4b7ceaea267480c5d9ae8a3cfe536
|
| 3 |
+
size 207602918
|
en/MeloTTS-English-v3/config.json
ADDED
|
@@ -0,0 +1,293 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"train": {
|
| 3 |
+
"segment_size": 16384
|
| 4 |
+
},
|
| 5 |
+
"data": {
|
| 6 |
+
"sampling_rate": 44100,
|
| 7 |
+
"filter_length": 2048,
|
| 8 |
+
"hop_length": 512,
|
| 9 |
+
"add_blank": true,
|
| 10 |
+
"n_speakers": 1,
|
| 11 |
+
"spk2id": {
|
| 12 |
+
"EN-Newest": 0
|
| 13 |
+
}
|
| 14 |
+
},
|
| 15 |
+
"model": {
|
| 16 |
+
"use_spk_conditioned_encoder": true,
|
| 17 |
+
"use_noise_scaled_mas": true,
|
| 18 |
+
"use_mel_posterior_encoder": false,
|
| 19 |
+
"use_duration_discriminator": true,
|
| 20 |
+
"inter_channels": 192,
|
| 21 |
+
"hidden_channels": 192,
|
| 22 |
+
"filter_channels": 768,
|
| 23 |
+
"n_heads": 2,
|
| 24 |
+
"n_layers": 6,
|
| 25 |
+
"n_layers_trans_flow": 3,
|
| 26 |
+
"kernel_size": 3,
|
| 27 |
+
"p_dropout": 0.1,
|
| 28 |
+
"resblock": "1",
|
| 29 |
+
"resblock_kernel_sizes": [
|
| 30 |
+
3,
|
| 31 |
+
7,
|
| 32 |
+
11
|
| 33 |
+
],
|
| 34 |
+
"resblock_dilation_sizes": [
|
| 35 |
+
[
|
| 36 |
+
1,
|
| 37 |
+
3,
|
| 38 |
+
5
|
| 39 |
+
],
|
| 40 |
+
[
|
| 41 |
+
1,
|
| 42 |
+
3,
|
| 43 |
+
5
|
| 44 |
+
],
|
| 45 |
+
[
|
| 46 |
+
1,
|
| 47 |
+
3,
|
| 48 |
+
5
|
| 49 |
+
]
|
| 50 |
+
],
|
| 51 |
+
"upsample_rates": [
|
| 52 |
+
8,
|
| 53 |
+
8,
|
| 54 |
+
2,
|
| 55 |
+
2,
|
| 56 |
+
2
|
| 57 |
+
],
|
| 58 |
+
"upsample_initial_channel": 512,
|
| 59 |
+
"upsample_kernel_sizes": [
|
| 60 |
+
16,
|
| 61 |
+
16,
|
| 62 |
+
8,
|
| 63 |
+
2,
|
| 64 |
+
2
|
| 65 |
+
],
|
| 66 |
+
"n_layers_q": 3,
|
| 67 |
+
"use_spectral_norm": false,
|
| 68 |
+
"gin_channels": 256
|
| 69 |
+
},
|
| 70 |
+
"num_languages": 8,
|
| 71 |
+
"num_tones": 16,
|
| 72 |
+
"symbols": [
|
| 73 |
+
"_",
|
| 74 |
+
"\"",
|
| 75 |
+
"(",
|
| 76 |
+
")",
|
| 77 |
+
"*",
|
| 78 |
+
"/",
|
| 79 |
+
":",
|
| 80 |
+
"AA",
|
| 81 |
+
"E",
|
| 82 |
+
"EE",
|
| 83 |
+
"En",
|
| 84 |
+
"N",
|
| 85 |
+
"OO",
|
| 86 |
+
"Q",
|
| 87 |
+
"V",
|
| 88 |
+
"[",
|
| 89 |
+
"\\",
|
| 90 |
+
"]",
|
| 91 |
+
"^",
|
| 92 |
+
"a",
|
| 93 |
+
"a:",
|
| 94 |
+
"aa",
|
| 95 |
+
"ae",
|
| 96 |
+
"ah",
|
| 97 |
+
"ai",
|
| 98 |
+
"an",
|
| 99 |
+
"ang",
|
| 100 |
+
"ao",
|
| 101 |
+
"aw",
|
| 102 |
+
"ay",
|
| 103 |
+
"b",
|
| 104 |
+
"by",
|
| 105 |
+
"c",
|
| 106 |
+
"ch",
|
| 107 |
+
"d",
|
| 108 |
+
"dh",
|
| 109 |
+
"dy",
|
| 110 |
+
"e",
|
| 111 |
+
"e:",
|
| 112 |
+
"eh",
|
| 113 |
+
"ei",
|
| 114 |
+
"en",
|
| 115 |
+
"eng",
|
| 116 |
+
"er",
|
| 117 |
+
"ey",
|
| 118 |
+
"f",
|
| 119 |
+
"g",
|
| 120 |
+
"gy",
|
| 121 |
+
"h",
|
| 122 |
+
"hh",
|
| 123 |
+
"hy",
|
| 124 |
+
"i",
|
| 125 |
+
"i0",
|
| 126 |
+
"i:",
|
| 127 |
+
"ia",
|
| 128 |
+
"ian",
|
| 129 |
+
"iang",
|
| 130 |
+
"iao",
|
| 131 |
+
"ie",
|
| 132 |
+
"ih",
|
| 133 |
+
"in",
|
| 134 |
+
"ing",
|
| 135 |
+
"iong",
|
| 136 |
+
"ir",
|
| 137 |
+
"iu",
|
| 138 |
+
"iy",
|
| 139 |
+
"j",
|
| 140 |
+
"jh",
|
| 141 |
+
"k",
|
| 142 |
+
"ky",
|
| 143 |
+
"l",
|
| 144 |
+
"m",
|
| 145 |
+
"my",
|
| 146 |
+
"n",
|
| 147 |
+
"ng",
|
| 148 |
+
"ny",
|
| 149 |
+
"o",
|
| 150 |
+
"o:",
|
| 151 |
+
"ong",
|
| 152 |
+
"ou",
|
| 153 |
+
"ow",
|
| 154 |
+
"oy",
|
| 155 |
+
"p",
|
| 156 |
+
"py",
|
| 157 |
+
"q",
|
| 158 |
+
"r",
|
| 159 |
+
"ry",
|
| 160 |
+
"s",
|
| 161 |
+
"sh",
|
| 162 |
+
"t",
|
| 163 |
+
"th",
|
| 164 |
+
"ts",
|
| 165 |
+
"ty",
|
| 166 |
+
"u",
|
| 167 |
+
"u:",
|
| 168 |
+
"ua",
|
| 169 |
+
"uai",
|
| 170 |
+
"uan",
|
| 171 |
+
"uang",
|
| 172 |
+
"uh",
|
| 173 |
+
"ui",
|
| 174 |
+
"un",
|
| 175 |
+
"uo",
|
| 176 |
+
"uw",
|
| 177 |
+
"v",
|
| 178 |
+
"van",
|
| 179 |
+
"ve",
|
| 180 |
+
"vn",
|
| 181 |
+
"w",
|
| 182 |
+
"x",
|
| 183 |
+
"y",
|
| 184 |
+
"z",
|
| 185 |
+
"zh",
|
| 186 |
+
"zy",
|
| 187 |
+
"~",
|
| 188 |
+
"æ",
|
| 189 |
+
"ç",
|
| 190 |
+
"ð",
|
| 191 |
+
"ø",
|
| 192 |
+
"ŋ",
|
| 193 |
+
"œ",
|
| 194 |
+
"ɐ",
|
| 195 |
+
"ɑ",
|
| 196 |
+
"ɒ",
|
| 197 |
+
"ɔ",
|
| 198 |
+
"ɕ",
|
| 199 |
+
"ə",
|
| 200 |
+
"ɛ",
|
| 201 |
+
"ɜ",
|
| 202 |
+
"ɡ",
|
| 203 |
+
"ɣ",
|
| 204 |
+
"ɥ",
|
| 205 |
+
"ɦ",
|
| 206 |
+
"ɪ",
|
| 207 |
+
"ɫ",
|
| 208 |
+
"ɬ",
|
| 209 |
+
"ɭ",
|
| 210 |
+
"ɯ",
|
| 211 |
+
"ɲ",
|
| 212 |
+
"ɵ",
|
| 213 |
+
"ɸ",
|
| 214 |
+
"ɹ",
|
| 215 |
+
"ɾ",
|
| 216 |
+
"ʁ",
|
| 217 |
+
"ʃ",
|
| 218 |
+
"ʊ",
|
| 219 |
+
"ʌ",
|
| 220 |
+
"ʎ",
|
| 221 |
+
"ʏ",
|
| 222 |
+
"ʑ",
|
| 223 |
+
"ʒ",
|
| 224 |
+
"ʝ",
|
| 225 |
+
"ʲ",
|
| 226 |
+
"ˈ",
|
| 227 |
+
"ˌ",
|
| 228 |
+
"ː",
|
| 229 |
+
"̃",
|
| 230 |
+
"̩",
|
| 231 |
+
"β",
|
| 232 |
+
"θ",
|
| 233 |
+
"ᄀ",
|
| 234 |
+
"ᄁ",
|
| 235 |
+
"ᄂ",
|
| 236 |
+
"ᄃ",
|
| 237 |
+
"ᄄ",
|
| 238 |
+
"ᄅ",
|
| 239 |
+
"ᄆ",
|
| 240 |
+
"ᄇ",
|
| 241 |
+
"ᄈ",
|
| 242 |
+
"ᄉ",
|
| 243 |
+
"ᄊ",
|
| 244 |
+
"ᄋ",
|
| 245 |
+
"ᄌ",
|
| 246 |
+
"ᄍ",
|
| 247 |
+
"ᄎ",
|
| 248 |
+
"ᄏ",
|
| 249 |
+
"ᄐ",
|
| 250 |
+
"ᄑ",
|
| 251 |
+
"ᄒ",
|
| 252 |
+
"ᅡ",
|
| 253 |
+
"ᅢ",
|
| 254 |
+
"ᅣ",
|
| 255 |
+
"ᅤ",
|
| 256 |
+
"ᅥ",
|
| 257 |
+
"ᅦ",
|
| 258 |
+
"ᅧ",
|
| 259 |
+
"ᅨ",
|
| 260 |
+
"ᅩ",
|
| 261 |
+
"ᅪ",
|
| 262 |
+
"ᅫ",
|
| 263 |
+
"ᅬ",
|
| 264 |
+
"ᅭ",
|
| 265 |
+
"ᅮ",
|
| 266 |
+
"ᅯ",
|
| 267 |
+
"ᅰ",
|
| 268 |
+
"ᅱ",
|
| 269 |
+
"ᅲ",
|
| 270 |
+
"ᅳ",
|
| 271 |
+
"ᅴ",
|
| 272 |
+
"ᅵ",
|
| 273 |
+
"ᆨ",
|
| 274 |
+
"ᆫ",
|
| 275 |
+
"ᆮ",
|
| 276 |
+
"ᆯ",
|
| 277 |
+
"ᆷ",
|
| 278 |
+
"ᆸ",
|
| 279 |
+
"ᆼ",
|
| 280 |
+
"ㄸ",
|
| 281 |
+
"!",
|
| 282 |
+
"?",
|
| 283 |
+
"…",
|
| 284 |
+
",",
|
| 285 |
+
".",
|
| 286 |
+
"'",
|
| 287 |
+
"-",
|
| 288 |
+
"¿",
|
| 289 |
+
"¡",
|
| 290 |
+
"SP",
|
| 291 |
+
"UNK"
|
| 292 |
+
]
|
| 293 |
+
}
|
en/MeloTTS-English-v3/source.txt
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
https://huggingface.co/myshell-ai/MeloTTS-English-v3
|
en/MeloTTS-English/.gitattributes
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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
|
en/MeloTTS-English/README.md
ADDED
|
@@ -0,0 +1,124 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
language:
|
| 4 |
+
- ko
|
| 5 |
+
pipeline_tag: text-to-speech
|
| 6 |
+
---
|
| 7 |
+
|
| 8 |
+
|
| 9 |
+
# MeloTTS
|
| 10 |
+
|
| 11 |
+
<a href="https://trendshift.io/repositories/8133" target="_blank"><img src="https://trendshift.io/api/badge/repositories/8133" alt="myshell-ai%2FMeloTTS | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a>
|
| 12 |
+
|
| 13 |
+
|
| 14 |
+
MeloTTS is a **high-quality multi-lingual** text-to-speech library by [MIT](https://www.mit.edu/) and [MyShell.ai](https://myshell.ai). Supported languages include:
|
| 15 |
+
|
| 16 |
+
|
| 17 |
+
|
| 18 |
+
| Model card | Example |
|
| 19 |
+
| --- | --- |
|
| 20 |
+
| [English](https://huggingface.co/myshell-ai/MeloTTS-English-v2) (American) | [Link](https://myshell-public-repo-host.s3.amazonaws.com/myshellttsbase/examples/en/EN-US/speed_1.0/sent_000.wav) |
|
| 21 |
+
| [English](https://huggingface.co/myshell-ai/MeloTTS-English-v2) (British) | [Link](https://myshell-public-repo-host.s3.amazonaws.com/myshellttsbase/examples/en/EN-BR/speed_1.0/sent_000.wav) |
|
| 22 |
+
| [English](https://huggingface.co/myshell-ai/MeloTTS-English-v2) (Indian) | [Link](https://myshell-public-repo-host.s3.amazonaws.com/myshellttsbase/examples/en/EN_INDIA/speed_1.0/sent_000.wav) |
|
| 23 |
+
| [English](https://huggingface.co/myshell-ai/MeloTTS-English-v2) (Australian) | [Link](https://myshell-public-repo-host.s3.amazonaws.com/myshellttsbase/examples/en/EN-AU/speed_1.0/sent_000.wav) |
|
| 24 |
+
| [English](https://huggingface.co/myshell-ai/MeloTTS-English-v2) (Default) | [Link](https://myshell-public-repo-host.s3.amazonaws.com/myshellttsbase/examples/en/EN-Default/speed_1.0/sent_000.wav) |
|
| 25 |
+
| [Spanish](https://huggingface.co/myshell-ai/MeloTTS-Spanish) | [Link](https://myshell-public-repo-host.s3.amazonaws.com/myshellttsbase/examples/es/ES/speed_1.0/sent_000.wav) |
|
| 26 |
+
| [French](https://huggingface.co/myshell-ai/MeloTTS-French) | [Link](https://myshell-public-repo-host.s3.amazonaws.com/myshellttsbase/examples/fr/FR/speed_1.0/sent_000.wav) |
|
| 27 |
+
| [Chinese](https://huggingface.co/myshell-ai/MeloTTS-Chinese) (mix EN) | [Link](https://myshell-public-repo-host.s3.amazonaws.com/myshellttsbase/examples/zh/ZH/speed_1.0/sent_008.wav) |
|
| 28 |
+
| [Japanese](https://huggingface.co/myshell-ai/MeloTTS-Japanese) | [Link](https://myshell-public-repo-host.s3.amazonaws.com/myshellttsbase/examples/jp/JP/speed_1.0/sent_000.wav) |
|
| 29 |
+
| [Korean](https://huggingface.co/myshell-ai/MeloTTS-Korean/) | [Link](https://myshell-public-repo-host.s3.amazonaws.com/myshellttsbase/examples/kr/KR/speed_1.0/sent_000.wav) |
|
| 30 |
+
|
| 31 |
+
Some other features include:
|
| 32 |
+
- The Chinese speaker supports `mixed Chinese and English`.
|
| 33 |
+
- Fast enough for `CPU real-time inference`.
|
| 34 |
+
|
| 35 |
+
## Authors
|
| 36 |
+
|
| 37 |
+
- [Wenliang Zhao](https://wl-zhao.github.io) at Tsinghua University
|
| 38 |
+
- [Xumin Yu](https://yuxumin.github.io) at Tsinghua University
|
| 39 |
+
- [Zengyi Qin](https://www.qinzy.tech) (project lead) at MIT and MyShell
|
| 40 |
+
|
| 41 |
+
**Citation**
|
| 42 |
+
```
|
| 43 |
+
@software{zhao2024melo,
|
| 44 |
+
author={Zhao, Wenliang and Yu, Xumin and Qin, Zengyi},
|
| 45 |
+
title = {MeloTTS: High-quality Multi-lingual Multi-accent Text-to-Speech},
|
| 46 |
+
url = {https://github.com/myshell-ai/MeloTTS},
|
| 47 |
+
year = {2023}
|
| 48 |
+
}
|
| 49 |
+
```
|
| 50 |
+
|
| 51 |
+
|
| 52 |
+
## Usage
|
| 53 |
+
|
| 54 |
+
### Without Installation
|
| 55 |
+
|
| 56 |
+
An unofficial [live demo](https://huggingface.co/spaces/mrfakename/MeloTTS) is hosted on Hugging Face Spaces.
|
| 57 |
+
|
| 58 |
+
#### Use it on MyShell
|
| 59 |
+
|
| 60 |
+
There are hundreds of TTS models on MyShell, much more than MeloTTS. See examples [here](https://github.com/myshell-ai/MeloTTS/blob/main/docs/quick_use.md#use-melotts-without-installation).
|
| 61 |
+
More can be found at the widget center of [MyShell.ai](https://app.myshell.ai/robot-workshop).
|
| 62 |
+
|
| 63 |
+
### Install and Use Locally
|
| 64 |
+
|
| 65 |
+
Follow the installation steps [here](https://github.com/myshell-ai/MeloTTS/blob/main/docs/install.md#linux-and-macos-install) before using the following snippet:
|
| 66 |
+
|
| 67 |
+
```python
|
| 68 |
+
from melo.api import TTS
|
| 69 |
+
|
| 70 |
+
# Speed is adjustable
|
| 71 |
+
speed = 1.0
|
| 72 |
+
|
| 73 |
+
# CPU is sufficient for real-time inference.
|
| 74 |
+
# You can set it manually to 'cpu' or 'cuda' or 'cuda:0' or 'mps'
|
| 75 |
+
device = 'auto' # Will automatically use GPU if available
|
| 76 |
+
|
| 77 |
+
# English
|
| 78 |
+
text = "Did you ever hear a folk tale about a giant turtle?"
|
| 79 |
+
model = TTS(language='EN', device=device)
|
| 80 |
+
speaker_ids = model.hps.data.spk2id
|
| 81 |
+
|
| 82 |
+
# American accent
|
| 83 |
+
output_path = 'en-us.wav'
|
| 84 |
+
model.tts_to_file(text, speaker_ids['EN-US'], output_path, speed=speed)
|
| 85 |
+
|
| 86 |
+
# British accent
|
| 87 |
+
output_path = 'en-br.wav'
|
| 88 |
+
model.tts_to_file(text, speaker_ids['EN-BR'], output_path, speed=speed)
|
| 89 |
+
|
| 90 |
+
# Indian accent
|
| 91 |
+
output_path = 'en-india.wav'
|
| 92 |
+
model.tts_to_file(text, speaker_ids['EN_INDIA'], output_path, speed=speed)
|
| 93 |
+
|
| 94 |
+
# Australian accent
|
| 95 |
+
output_path = 'en-au.wav'
|
| 96 |
+
model.tts_to_file(text, speaker_ids['EN-AU'], output_path, speed=speed)
|
| 97 |
+
|
| 98 |
+
# Default accent
|
| 99 |
+
output_path = 'en-default.wav'
|
| 100 |
+
model.tts_to_file(text, speaker_ids['EN-Default'], output_path, speed=speed)
|
| 101 |
+
|
| 102 |
+
```
|
| 103 |
+
|
| 104 |
+
|
| 105 |
+
## Join the Community
|
| 106 |
+
|
| 107 |
+
**Open Source AI Grant**
|
| 108 |
+
|
| 109 |
+
We are actively sponsoring open-source AI projects. The sponsorship includes GPU resources, fundings and intellectual support (collaboration with top research labs). We welcome both reseach and engineering projects, as long as the open-source community needs them. Please contact [Zengyi Qin](https://www.qinzy.tech/) if you are interested.
|
| 110 |
+
|
| 111 |
+
**Contributing**
|
| 112 |
+
|
| 113 |
+
If you find this work useful, please consider contributing to the GitHub [repo](https://github.com/myshell-ai/MeloTTS).
|
| 114 |
+
|
| 115 |
+
- Many thanks to [@fakerybakery](https://github.com/fakerybakery) for adding the Web UI and CLI part.
|
| 116 |
+
|
| 117 |
+
## License
|
| 118 |
+
|
| 119 |
+
This library is under MIT License, which means it is free for both commercial and non-commercial use.
|
| 120 |
+
|
| 121 |
+
## Acknowledgements
|
| 122 |
+
|
| 123 |
+
This implementation is based on [TTS](https://github.com/coqui-ai/TTS), [VITS](https://github.com/jaywalnut310/vits), [VITS2](https://github.com/daniilrobnikov/vits2) and [Bert-VITS2](https://github.com/fishaudio/Bert-VITS2). We appreciate their awesome work.
|
| 124 |
+
|
en/MeloTTS-English/checkpoint.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:acd278040eaf9536908e2b965273df5a731c44d8f0da66cc5fed7972772ed23c
|
| 3 |
+
size 207860748
|