Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

v0.20.1 #3156

Merged
merged 20 commits into from
Nov 7, 2023
Merged

v0.20.1 #3156

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
20 commits
Select commit Hold shift + click to select a range
9d54bd7
Fixup XTTS
erogol Nov 6, 2023
9bbf6eb
Drop use_ne_hifigan
erogol Nov 6, 2023
5d418bb
Update docs
erogol Nov 6, 2023
f0cb19e
Drop diffusion from XTTS (#3150)
erogol Nov 6, 2023
9942000
Update XTTS v2 recipe model files
Edresson Nov 6, 2023
459ad70
Add support for multiples speaker references on XTTS inference
Edresson Nov 6, 2023
00294ff
Update XTTS docs
Edresson Nov 6, 2023
72b2bac
Load reference in 24khz to avoid issued with multiple sr references
Edresson Nov 6, 2023
1b6f8d0
Update unit tests and recipes
Edresson Nov 6, 2023
f444f29
Add multiples references on xtts inference tests
Edresson Nov 6, 2023
b146de4
Bug fix on XTTS v2.0 Trainer
Edresson Nov 6, 2023
09fb317
Remove unused code
Edresson Nov 6, 2023
cabff9f
Update XTTS v2.0 recipe
Edresson Nov 6, 2023
13243df
Update XTTS v1.1 files
Edresson Nov 6, 2023
2470599
Drop XTTS v1
Edresson Nov 6, 2023
905900a
Update XTTS v1.1 recipe
Edresson Nov 6, 2023
5f9ab6c
Fix style
Edresson Nov 6, 2023
5e992d8
Merge pull request #3149 from coqui-ai/fixup_xtts_v2
erogol Nov 7, 2023
cbdbc44
Fix XTTS v2.0 training recipe (#3154)
Edresson Nov 7, 2023
f846a9f
Update to v0.20.1
erogol Nov 7, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
24 changes: 6 additions & 18 deletions TTS/.models.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -10,34 +10,22 @@
"https://coqui.gateway.scarf.sh/hf-coqui/XTTS-v2/main/vocab.json",
"https://coqui.gateway.scarf.sh/hf-coqui/XTTS-v2/main/hash.md5"
],
"model_hash": "6a09d1ad43896f06041ed8195956c9698f13b6189dc80f1c74bdc2b8e8d15324",
"default_vocoder": null,
"commit": "480a6cdf7",
"license": "CPML",
"contact": "[email protected]",
"tos_required": true
},
"xtts_v1": {
"description": "XTTS-v1 by Coqui with 13 languages and cross-language voice cloning.",
"hf_url": [
"https://coqui.gateway.scarf.sh/hf-coqui/XTTS-v1/hifigan/model.pth",
"https://coqui.gateway.scarf.sh/hf-coqui/XTTS-v1/hifigan/config.json",
"https://coqui.gateway.scarf.sh/hf-coqui/XTTS-v1/hifigan/vocab.json"
],
"default_vocoder": null,
"commit": "e5140314",
"license": "CPML",
"contact": "[email protected]",
"tos_required": true
},
"xtts_v1.1": {
"description": "XTTS-v1.1 by Coqui with 14 languages, cross-language voice cloning and reference leak fixed.",
"hf_url": [
"https://coqui.gateway.scarf.sh/hf-coqui/XTTS-v1/v1.1.1/model.pth",
"https://coqui.gateway.scarf.sh/hf-coqui/XTTS-v1/v1.1.1/config.json",
"https://coqui.gateway.scarf.sh/hf-coqui/XTTS-v1/v1.1.1/vocab.json",
"https://coqui.gateway.scarf.sh/hf-coqui/XTTS-v1/v1.1.1/hash.md5"
"https://coqui.gateway.scarf.sh/hf-coqui/XTTS-v1/v1.1.2/model.pth",
"https://coqui.gateway.scarf.sh/hf-coqui/XTTS-v1/v1.1.2/config.json",
"https://coqui.gateway.scarf.sh/hf-coqui/XTTS-v1/v1.1.2/vocab.json",
"https://coqui.gateway.scarf.sh/hf-coqui/XTTS-v1/v1.1.2/hash.md5"
],
"model_hash": "ae9e4b39e095fd5728fe7f7931ec66ad",
"model_hash": "7c62beaf58d39b729de287330dc254e7b515677416839b649a50e7cf74c3df59",
"default_vocoder": null,
"commit": "82910a63",
"license": "CPML",
Expand Down
2 changes: 1 addition & 1 deletion TTS/VERSION
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1 +1 @@
0.20.0
0.20.1
2 changes: 1 addition & 1 deletion TTS/tts/configs/xtts_config.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -30,7 +30,7 @@ class XttsConfig(BaseTTSConfig):
which in turn is used to divide the score of the sequence. Since the score is the log likelihood of the sequence (i.e. negative),
length_penalty > 0.0 promotes longer sequences, while length_penalty < 0.0 encourages shorter sequences.

reperation_penalty (float):
repetition_penalty (float):
The parameter for repetition penalty. 1.0 means no penalty. Defaults to `2.0`.

top_p (float):
Expand Down
2 changes: 1 addition & 1 deletion TTS/tts/layers/tortoise/dpm_solver.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1548,4 +1548,4 @@ def expand_dims(v, dims):
Returns:
a PyTorch tensor with shape [N, 1, 1, ..., 1] and the total dimension is `dims`.
"""
return v[(...,) + (None,) * (dims - 1)]
return v[(...,) + (None,) * (dims - 1)]
Loading