Hugging Face's logo

VoiceHub
/
DACFlow-EN-10k

Text-to-Speech
AudioSeal
Safetensors
English
zero-shot
voice-cloning
english
flow-matching
diffusion-transformer
dacvae
Model card Files
xet
 Community
kadirnar commited on
Commit
a15ee8a
·
verified ·
1 Parent(s): 066699e

showcase: refresh the card

Browse files
Files changed (2) hide show
  1. README.md +1 -1
  2. showcase.json +9 -2
README.md CHANGED
@@ -274,7 +274,7 @@ UTMOS** are better):
274
 
275
  | Checkpoint | echo-dev WER ↓ | echo-dev SIM-o ↑ | echo-dev UTMOS ↑ (real speech: 4.20) | seed-dev WER ↓ | seed-dev SIM-o ↑ | seed-dev UTMOS ↑ (real speech: 3.52) | Samples | Weights |
276
  |---|---:|---:|---:|---:|---:|---:|---|---|
277
- | **step 170k** (newest) | - | - | - | - | - | - | [listen](#listen) | [files](https://huggingface.co/VoiceHub/DACFlow-EN-10k/tree/main/checkpoints/step_0170000) |
278
  | step 160k | 0.81 % | 0.796 | 3.98 | 1.58 % | 0.349 | 3.66 | [listen](#listen) | [files](https://huggingface.co/VoiceHub/DACFlow-EN-10k/tree/main/checkpoints/step_0160000) |
279
  | step 150k | 0.53 % | 0.794 | 3.93 | - | - | - | [listen](#listen) | [files](https://huggingface.co/VoiceHub/DACFlow-EN-10k/tree/main/checkpoints/step_0150000) |
280
  | step 140k | 0.58 % | 0.793 | 3.92 | 1.60 % | 0.404 | 3.81 | [listen](#listen) | [files](https://huggingface.co/VoiceHub/DACFlow-EN-10k/tree/main/checkpoints/step_0140000) |
 
274
 
275
  | Checkpoint | echo-dev WER ↓ | echo-dev SIM-o ↑ | echo-dev UTMOS ↑ (real speech: 4.20) | seed-dev WER ↓ | seed-dev SIM-o ↑ | seed-dev UTMOS ↑ (real speech: 3.52) | Samples | Weights |
276
  |---|---:|---:|---:|---:|---:|---:|---|---|
277
+ | **step 170k** (newest) | 1.01 % | 0.796 | 3.97 | - | - | - | [listen](#listen) | [files](https://huggingface.co/VoiceHub/DACFlow-EN-10k/tree/main/checkpoints/step_0170000) |
278
  | step 160k | 0.81 % | 0.796 | 3.98 | 1.58 % | 0.349 | 3.66 | [listen](#listen) | [files](https://huggingface.co/VoiceHub/DACFlow-EN-10k/tree/main/checkpoints/step_0160000) |
279
  | step 150k | 0.53 % | 0.794 | 3.93 | - | - | - | [listen](#listen) | [files](https://huggingface.co/VoiceHub/DACFlow-EN-10k/tree/main/checkpoints/step_0150000) |
280
  | step 140k | 0.58 % | 0.793 | 3.92 | 1.60 % | 0.404 | 3.81 | [listen](#listen) | [files](https://huggingface.co/VoiceHub/DACFlow-EN-10k/tree/main/checkpoints/step_0140000) |
showcase.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "card_sha": "3f0ebcc2719efae2",
3
  "checkpoints": {
4
  "en_base/step_0020000": {
5
  "added": "2026-10-03T02:01:41Z",
@@ -1930,7 +1930,14 @@
1930
  },
1931
  "folder": "checkpoints/step_0170000",
1932
  "lineage": [],
1933
- "metrics": {},
 
 
 
 
 
 
 
1934
  "note": "Main model (M4 base pretraining): the 206 M base preset on the full provided data",
1935
  "params_m": 206.41,
1936
  "preset": "base",
 
1
  {
2
+ "card_sha": "4c04d9fd56669de7",
3
  "checkpoints": {
4
  "en_base/step_0020000": {
5
  "added": "2026-10-03T02:01:41Z",
 
1930
  },
1931
  "folder": "checkpoints/step_0170000",
1932
  "lineage": [],
1933
+ "metrics": {
1934
+ "echo_dev": {
1935
+ "n": 260,
1936
+ "sim_o": 0.7958178685261653,
1937
+ "utmos": 3.9733734222558827,
1938
+ "wer": 0.010128913443830571
1939
+ }
1940
+ },
1941
  "note": "Main model (M4 base pretraining): the 206 M base preset on the full provided data",
1942
  "params_m": 206.41,
1943
  "preset": "base",