riaz.somc/transformers
1
0
Fork 0
mirror of https://github.com/huggingface/transformers.git synced 2025-08-01 02:31:11 +06:00
Code Issues Actions 3 Packages Projects Releases Wiki Activity

[DOCS] MusicGen Docs Update (#25510)

Browse Source 
* docs: note token limitations for MusicGen

* docs: note token limitations for MusicGen

* docs: fix token count with token limitations for MusicGen
This commit is contained in:
Blake Wyatt 2023-08-22 02:22:45 -04:00 committed by GitHub
parent 182b83749a
commit 6a314ea7cd
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 4 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
docs/source/en/model_doc/musicgen.md
View File

@ -53,6 +53,10 @@ better results than greedy, thus we encourage sampling mode to be used where pos
and can be explicitly specified by setting `do_sample=True` in the call to [`MusicgenForConditionalGeneration.generate`], and can be explicitly specified by setting `do_sample=True` in the call to [`MusicgenForConditionalGeneration.generate`],
or by overriding the model's generation config (see below). or by overriding the model's generation config (see below).
Generation is limited by the sinusoidal positional embeddings to 30 second inputs. Meaning, MusicGen cannot generate more
than 30 seconds of audio (1503 tokens), and input audio passed by Audio-Prompted Generation contributes to this limit so,
given an input of 20 seconds of audio, MusicGen cannot generate more than 10 seconds of additional audio.
### Unconditional Generation ### Unconditional Generation
The inputs for unconditional (or 'null') generation can be obtained through the method The inputs for unconditional (or 'null') generation can be obtained through the method