Spaces:
Running
on
A10G
Running
on
A10G
updated requirements
Browse files- descriptions.py +1 -0
- requirements.txt +1 -0
descriptions.py
CHANGED
@@ -1,5 +1,6 @@
|
|
1 |
top_md = """
|
2 |
# VALL-E X
|
|
|
3 |
VALL-E X can synthesize high-quality personalized speech with only a 3-second enrolled recording of
|
4 |
an unseen speaker as an acoustic prompt, even in another language for a monolingual speaker.<br>
|
5 |
This implementation supports zero-shot, mono-lingual/cross-lingual text-to-speech functionality of three languages (English, Chinese, Japanese)<br>
|
|
|
1 |
top_md = """
|
2 |
# VALL-E X
|
3 |
+
[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1yyD_sz531QntLKowMHo-XxorsFBCfKul?usp=sharing)
|
4 |
VALL-E X can synthesize high-quality personalized speech with only a 3-second enrolled recording of
|
5 |
an unseen speaker as an acoustic prompt, even in another language for a monolingual speaker.<br>
|
6 |
This implementation supports zero-shot, mono-lingual/cross-lingual text-to-speech functionality of three languages (English, Chinese, Japanese)<br>
|
requirements.txt
CHANGED
@@ -14,6 +14,7 @@ jieba
|
|
14 |
eng_to_ipa
|
15 |
jieba
|
16 |
SudachiPy
|
|
|
17 |
openai-whisper
|
18 |
phonemizer
|
19 |
matplotlib
|
|
|
14 |
eng_to_ipa
|
15 |
jieba
|
16 |
SudachiPy
|
17 |
+
nltk
|
18 |
openai-whisper
|
19 |
phonemizer
|
20 |
matplotlib
|