Spaces:
Paused
Paused
Update app.py
Browse files
app.py
CHANGED
@@ -111,25 +111,25 @@ with gr.Blocks(css=css) as demo_blocks:
|
|
111 |
info = "Language that you want to test"
|
112 |
)
|
113 |
|
114 |
-
|
115 |
-
## Datasets and models details
|
116 |
-
|
117 |
-
### English
|
118 |
-
|
119 |
-
* **Model**: [VITS-ljs](https://huggingface.co/kakao-enterprise/vits-ljs)
|
120 |
-
* **Dataset**: [British Isles Accent](https://huggingface.co/datasets/ylacombe/english_dialects). For each accent, we used 100 to 150 samples of a single speaker to finetune [VITS-ljs](https://huggingface.co/kakao-enterprise/vits-ljs).
|
121 |
-
|
122 |
-
### Spanish
|
123 |
-
|
124 |
-
* **Model**: [Spanish MMS TTS](https://huggingface.co/facebook/mms-tts-spa). This model is part of Facebook's [Massively Multilingual Speech](https://arxiv.org/abs/2305.13516) project, aiming to
|
125 |
-
provide speech technology across a diverse range of languages. You can find more details about the supported languages and their ISO 639-3 codes in the [MMS Language Coverage Overview](https://dl.fbaipublicfiles.com/mms/misc/language_coverage_mms.html),
|
126 |
-
and see all MMS-TTS checkpoints on the Hugging Face Hub: [facebook/mms-tts](https://huggingface.co/models?sort=trending&search=facebook%2Fmms-tts).
|
127 |
-
* **Datasets**: For each accent, we used 100 to 150 samples of a single speaker to finetune the model.
|
128 |
-
|
129 |
-
|
130 |
-
|
131 |
-
|
132 |
-
|
133 |
|
134 |
with gr.Column():
|
135 |
outputs = []
|
|
|
111 |
info = "Language that you want to test"
|
112 |
)
|
113 |
|
114 |
+
gr.Markdown("""
|
115 |
+
## Datasets and models details
|
116 |
+
|
117 |
+
### English
|
118 |
+
|
119 |
+
* **Model**: [VITS-ljs](https://huggingface.co/kakao-enterprise/vits-ljs)
|
120 |
+
* **Dataset**: [British Isles Accent](https://huggingface.co/datasets/ylacombe/english_dialects). For each accent, we used 100 to 150 samples of a single speaker to finetune [VITS-ljs](https://huggingface.co/kakao-enterprise/vits-ljs).
|
121 |
+
|
122 |
+
### Spanish
|
123 |
+
|
124 |
+
* **Model**: [Spanish MMS TTS](https://huggingface.co/facebook/mms-tts-spa). This model is part of Facebook's [Massively Multilingual Speech](https://arxiv.org/abs/2305.13516) project, aiming to
|
125 |
+
provide speech technology across a diverse range of languages. You can find more details about the supported languages and their ISO 639-3 codes in the [MMS Language Coverage Overview](https://dl.fbaipublicfiles.com/mms/misc/language_coverage_mms.html),
|
126 |
+
and see all MMS-TTS checkpoints on the Hugging Face Hub: [facebook/mms-tts](https://huggingface.co/models?sort=trending&search=facebook%2Fmms-tts).
|
127 |
+
* **Datasets**: For each accent, we used 100 to 150 samples of a single speaker to finetune the model.
|
128 |
+
- [Colombian Spanish TTS dataset](https://huggingface.co/datasets/ylacombe/google-colombian-spanish).
|
129 |
+
- [Argentinian Spanish TTS dataset](https://huggingface.co/datasets/ylacombe/google-argentinian-spanish).
|
130 |
+
- [Chilean Spanish TTS dataset](https://huggingface.co/datasets/ylacombe/google-chilean-spanish).
|
131 |
+
|
132 |
+
""")
|
133 |
|
134 |
with gr.Column():
|
135 |
outputs = []
|