trending/YuE
1
0
Fork 0
mirror of https://github.com/multimodal-art-projection/YuE.git synced 2026-10-02 01:34:32 +08:00
Code Issues Packages Projects Releases Wiki Activity

update readme

Browse Source
This commit is contained in:
a43992899
2025-02-02 02:20:19 +08:00
parent 5206c546eb
commit e6641f5fbe
2 changed files with 6 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.gitignore
+3
View File
@@ -160,3 +160,6 @@ cython_debug/
# and can be added to the global gitignore or merged into this file. For a more nuclear
# option (not recommended) you can uncomment the following to ignore the entire idea folder.
#.idea/
inference/output
inference/xcodec_mini_infer
README.md
+3 -6
View File
@@ -112,11 +112,10 @@ python infer.py \
--genre_txt ../genre.txt \
--lyrics_txt ../lyrics.txt \
--run_n_segments 2 \
--stage2_batch_size 4 \
--stage2_batch_size 16 \
--output_dir ./output \
--cuda_idx 0 \
--max_new_tokens 3000 \
--seed 42
```
We also support music in-context-learning (provide a reference song), there are 2 types: single-track (mix/vocal/instrumental) and dual-track.
@@ -145,11 +144,10 @@ python infer.py \
--genre_txt ../genre.txt \
--lyrics_txt ../lyrics.txt \
--run_n_segments 2 \
--stage2_batch_size 4 \
--stage2_batch_size 16 \
--output_dir ./output \
--cuda_idx 0 \
--max_new_tokens 3000 \
--seed 42 \
--use_dual_tracks_prompt \
--vocal_track_prompt_path ../pop.00001.Vocals.mp3 \
--instrumental_track_prompt_path ../pop.00001.Instrumental.mp3 \
@@ -170,11 +168,10 @@ python infer.py \
--genre_txt ../genre.txt \
--lyrics_txt ../lyrics.txt \
--run_n_segments 2 \
--stage2_batch_size 4 \
--stage2_batch_size 16 \
--output_dir ./output \
--cuda_idx 0 \
--max_new_tokens 3000 \
--seed 42 \
--use_audio_prompt \
--audio_prompt_path ../pop.00001.mp3 \
--prompt_start_time 0 \