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

Fix loading Bark #2893

Merged
merged 2 commits into from
Aug 26, 2023
Merged

Fix loading Bark #2893

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
81bbcb0
Fixup hubert path
erogol Aug 26, 2023
c537eb9
Make style
erogol Aug 26, 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
8 changes: 5 additions & 3 deletions TTS/.models.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -15,8 +15,10 @@
"hf_url": [
"https://coqui.gateway.scarf.sh/hf/bark/coarse_2.pt",
"https://coqui.gateway.scarf.sh/hf/bark/fine_2.pt",
"https://app.coqui.ai/tts_model/bark_text_2",
"https://coqui.gateway.scarf.sh/hf/bark/config.json"
"https://app.coqui.ai/tts_model/text_2.pt",
"https://coqui.gateway.scarf.sh/hf/bark/config.json",
"https://coqui.gateway.scarf.sh/hf/bark/hubert.pt",
"https://coqui.gateway.scarf.sh/hf/bark/tokenizer.pth"
],
"default_vocoder": null,
"commit": "e9a1953e",
Expand Down Expand Up @@ -238,7 +240,7 @@
"tortoise-v2": {
"description": "Tortoise tts model https://github.com/neonbjb/tortoise-tts",
"github_rls_url": [
"https://app.coqui.ai/tts_model/tortoise",
"https://app.coqui.ai/tts_model/autoregressive.pth",
"https://coqui.gateway.scarf.sh/v0.14.1_models/clvp2.pth",
"https://coqui.gateway.scarf.sh/v0.14.1_models/cvvp.pth",
"https://coqui.gateway.scarf.sh/v0.14.1_models/diffusion_decoder.pth",
Expand Down
6 changes: 6 additions & 0 deletions TTS/tts/models/bark.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -246,6 +246,8 @@ def load_checkpoint(
text_model_path=None,
coarse_model_path=None,
fine_model_path=None,
hubert_model_path=None,
hubert_tokenizer_path=None,
eval=False,
strict=True,
**kwargs,
Expand All @@ -267,10 +269,14 @@ def load_checkpoint(
text_model_path = text_model_path or os.path.join(checkpoint_dir, "text_2.pt")
coarse_model_path = coarse_model_path or os.path.join(checkpoint_dir, "coarse_2.pt")
fine_model_path = fine_model_path or os.path.join(checkpoint_dir, "fine_2.pt")
hubert_model_path = hubert_model_path or os.path.join(checkpoint_dir, "hubert.pt")
hubert_tokenizer_path = hubert_tokenizer_path or os.path.join(checkpoint_dir, "tokenizer.pth")

self.config.LOCAL_MODEL_PATHS["text"] = text_model_path
self.config.LOCAL_MODEL_PATHS["coarse"] = coarse_model_path
self.config.LOCAL_MODEL_PATHS["fine"] = fine_model_path
self.config.LOCAL_MODEL_PATHS["hubert"] = hubert_model_path
self.config.LOCAL_MODEL_PATHS["hubert_tokenizer"] = hubert_tokenizer_path

self.load_bark_models()

Expand Down
3 changes: 2 additions & 1 deletion TTS/tts/utils/synthesis.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,7 +18,8 @@ def compute_style_mel(style_wav, ap, cuda=False, device="cpu"):
if cuda:
device = "cuda"
style_mel = torch.FloatTensor(
ap.melspectrogram(ap.load_wav(style_wav, sr=ap.sample_rate)), device=device,
ap.melspectrogram(ap.load_wav(style_wav, sr=ap.sample_rate)),
device=device,
).unsqueeze(0)
return style_mel

Expand Down