shangeth
/

Wren-TTS-360M-en

speech-synthesis

Model card Files Files and versions

Wren-TTS-360M-en

854 MB

Ctrl+K

Ctrl+K

1 contributor

History: 9 commits

shangeth's picture

Update model card: drop v1 naming

d616110 verified 23 days ago

.gitattributes

1.52 kB
initial commit about 1 month ago
README.md

8.23 kB
Update model card: drop v1 naming 23 days ago
added_tokens.json

93 Bytes
v1 delay-pattern (k=8): replace flat k=3 with MusicGen-style delay about 1 month ago
config.json

528 Bytes
v1 delay-pattern (k=8): replace flat k=3 with MusicGen-style delay about 1 month ago
configuration_wren.py

1.32 kB
v1 delay-pattern (k=8): replace flat k=3 with MusicGen-style delay about 1 month ago
merges.txt

466 kB
Upload Wren checkpoint about 1 month ago
model.safetensors

850 MB
xet

v1 weights → v2.1 best.pt (epoch 9): 4-corpus training, +15% rel WER on libritts test_clean about 1 month ago
modeling_wren.py

11.1 kB
Hide importlib fallback from transformers' check_imports static scanner about 1 month ago
processing_wren.py

1.99 kB
v1 delay-pattern (k=8): replace flat k=3 with MusicGen-style delay about 1 month ago
processor_config.json

114 Bytes
Upload Wren checkpoint about 1 month ago
special_tokens_map.json

963 Bytes
v1 delay-pattern (k=8): replace flat k=3 with MusicGen-style delay about 1 month ago
tokenizer.json

3.52 MB
v1 delay-pattern (k=8): replace flat k=3 with MusicGen-style delay about 1 month ago
tokenizer_config.json

3.99 kB
v1 delay-pattern (k=8): replace flat k=3 with MusicGen-style delay about 1 month ago
vocab.json

801 kB
Upload Wren checkpoint about 1 month ago