gitea-mirror/F5-TTS
1
0
Fork 0
mirror of https://github.com/SWivid/F5-TTS.git synced 2026-01-15 06:23:22 -08:00
Code Issues Packages Projects Releases Wiki Activity

address #76 #29

Browse Source
This commit is contained in:
SWivid
2024-10-15 03:45:14 +08:00
parent 2cd03c9134
commit 12ef9d23f3
3 changed files with 2 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
README.md
View File

@@ -33,8 +33,6 @@ Install other packages:
pip install -r requirements.txt
```
**Note**: install numpy with version < 2.x, e.g. `pip install numpy==1.22.0`.
## Prepare Dataset
Example data processing scripts for Emilia and Wenetspeech4TTS, and you may tailor your own one along with a Dataset class in `model/dataset.py`.

2
gradio_app.py
View File

@@ -280,7 +280,7 @@ def infer_batch(ref_audio, ref_text, gen_text_batches, exp_name, remove_silence,
return (target_sample_rate, final_wave), spectrogram_path
def infer(ref_audio_orig, ref_text, gen_text, exp_name, remove_silence, custom_split_words):
def infer(ref_audio_orig, ref_text, gen_text, exp_name, remove_silence, custom_split_words=''):
if not custom_split_words.strip():
custom_words = [word.strip() for word in custom_split_words.split(',')]
global SPLIT_WORDS

1
requirements.txt
View File

@@ -12,6 +12,7 @@ jieba
jiwer
librosa
matplotlib
numpy==1.23.5
pydub
pypinyin
safetensors