Text-to-Speech
F5-TTS
English
tts
zero-shot-tts
diffusion-transformer
flow-matching
voice-cloning
speech-synthesis
english
comfyui
int8
convrot
Instructions to use drbaph/Raon-OpenTTS-comfyui with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- F5-TTS
How to use drbaph/Raon-OpenTTS-comfyui with F5-TTS:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
Upload Raon-OpenTTS-1B/config.yaml with huggingface_hub
Browse files- Raon-OpenTTS-1B/config.yaml +30 -0
Raon-OpenTTS-1B/config.yaml
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
model:
|
| 2 |
+
name: 1B
|
| 3 |
+
tokenizer: custom
|
| 4 |
+
tokenizer_path: vocab.txt
|
| 5 |
+
backbone: DiT
|
| 6 |
+
arch:
|
| 7 |
+
dim: 1408
|
| 8 |
+
depth: 28
|
| 9 |
+
heads: 24
|
| 10 |
+
ff_mult: 4
|
| 11 |
+
text_dim: 512
|
| 12 |
+
text_mask_padding: True
|
| 13 |
+
qk_norm: null
|
| 14 |
+
conv_layers: 4
|
| 15 |
+
pe_attn_head: null
|
| 16 |
+
attn_mask_enabled: False
|
| 17 |
+
checkpoint_activations: False
|
| 18 |
+
logit_softcapping: null
|
| 19 |
+
post_norm: False
|
| 20 |
+
norm_type: rmsnorm
|
| 21 |
+
mel_spec:
|
| 22 |
+
target_sample_rate: 16000
|
| 23 |
+
n_mel_channels: 80
|
| 24 |
+
hop_length: 256
|
| 25 |
+
win_length: 1024
|
| 26 |
+
n_fft: 1024
|
| 27 |
+
mel_spec_type: sbhifigan16k
|
| 28 |
+
vocoder:
|
| 29 |
+
is_local: True
|
| 30 |
+
local_path: null
|