3.22 GB

Ctrl+K

1 contributor

History: 15 commits

kadirnar

Add vocos_v2_balanced.pt: Vocos v2 trained further on speaker-balanced batches (male / female voices)

0906c46 verified 26 days ago

mlx
MLX: Vocos fine-tune (vocos-ft), float32 27 days ago
onnx
ONNX config: file sizes of the published graphs 28 days ago
.gitattributes

1.63 kB
Drifting TTS Turkish v3.1 29 days ago
README.md

72.2 kB
Add vocos_v2_balanced.pt: Vocos v2 trained further on speaker-balanced batches (male / female voices) 26 days ago
SPEAKERS.md

63.1 kB
Model card: all speaker IDs with WER, CER, DNSMOS, UTMOSv2; MLX; WebGPU update 28 days ago
bigvgan_base_ft.pt

56.3 MB
xet

Add bigvgan_base_ft.pt: BigVGAN-base fine-tuned on the v3.1 mels 28 days ago
bigvgan_v2_ft.pt

450 MB
xet

Drifting TTS Turkish v3.1 29 days ago
config.yaml

1.48 kB
Drifting TTS Turkish v3.1 29 days ago
drifting_tts_v3.1.pt

271 MB
xet

Drifting TTS Turkish v3.1 29 days ago
drifting_tts_v3.2.pt

271 MB
xet

Release v3.2: sampled intonation (drifting prosody model), Vocos v2, punctuation pauses 26 days ago
drifting_tts_v3.pt

271 MB
xet

Drifting TTS Turkish v3.1 29 days ago
prosody_drift_v3.2.pt

32.5 MB
xet

Release v3.2: sampled intonation (drifting prosody model), Vocos v2, punctuation pauses 26 days ago
speakers.csv

52 kB
Model card: all speaker IDs with WER, CER, DNSMOS, UTMOSv2; MLX; WebGPU update 28 days ago
vocos_ft.pt

54.4 MB
xet

Add vocos_ft.pt: Vocos fine-tuned on the v3.1 (BigVGAN-style) mels 28 days ago
vocos_v2.pt

54.4 MB
xet

Release v3.2: sampled intonation (drifting prosody model), Vocos v2, punctuation pauses 26 days ago
vocos_v2_balanced.pt

54.4 MB
xet

Add vocos_v2_balanced.pt: Vocos v2 trained further on speaker-balanced batches (male / female voices) 26 days ago
voices.json

233 Bytes
Drifting TTS Turkish v3.1 29 days ago