Update README.md
Browse files
README.md
CHANGED
|
@@ -11,7 +11,7 @@ base_model:
|
|
| 11 |
pipeline_tag: text-to-speech
|
| 12 |
---
|
| 13 |
|
| 14 |
-
Here are
|
| 15 |
|
| 16 |
Numbers cannot be understood by models. Convert numbers to words.
|
| 17 |
|
|
@@ -44,15 +44,3 @@ Model: hf://AsmoKoskinen/F5-TTS_Finnish_Model/model_commonvoice_fi_librivox_fi_v
|
|
| 44 |
Vocab: hf://AsmoKoskinen/F5-TTS_Finnish_Model/model_commonvoice_fi_librivox_fi_vox_populi_fi_20241217/vocab.txt
|
| 45 |
|
| 46 |
--- --- ---
|
| 47 |
-
|
| 48 |
-
The third round is based on the Common Voice, LibriVox and Vox Populi Finnish data sets, same as the second round. This one is no better.
|
| 49 |
-
|
| 50 |
-
- 20250125
|
| 51 |
-
|
| 52 |
-
- Speakers: Several speakers from different corpus
|
| 53 |
-
|
| 54 |
-
- Use these with "f5-tts_infer-gradio":
|
| 55 |
-
|
| 56 |
-
Model: hf://AsmoKoskinen/F5-TTS_Finnish_Model/model_commonvoice_fi_librivox_fi_vox_populi_fi_20250125/model_last_20250125.safetensors
|
| 57 |
-
|
| 58 |
-
Vocab: hf://AsmoKoskinen/F5-TTS_Finnish_Model/model_commonvoice_fi_librivox_fi_vox_populi_fi_20250125/vocab.txt
|
|
|
|
| 11 |
pipeline_tag: text-to-speech
|
| 12 |
---
|
| 13 |
|
| 14 |
+
Here are two Finnish models of the F5-TTS, listen speech samples for models.
|
| 15 |
|
| 16 |
Numbers cannot be understood by models. Convert numbers to words.
|
| 17 |
|
|
|
|
| 44 |
Vocab: hf://AsmoKoskinen/F5-TTS_Finnish_Model/model_commonvoice_fi_librivox_fi_vox_populi_fi_20241217/vocab.txt
|
| 45 |
|
| 46 |
--- --- ---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|