speedyspeech code adapt for npu #3804
Merged
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
zxcd
reviewed
Jul 8, 2024
paddlespeech/t2s/exps/synthesize.py
Outdated
| @@ -219,12 +219,18 @@ def parse_args(): | |||
| ) | |||
| # other | |||
| parser.add_argument( | |||
| "--ngpu", type=int, default=1, help="if ngpu == 0, use cpu or xpu.") | |||
| "--ngpu", type=int, default=1, help="if ngpu == 0, use cpu or xpu or npu.") | |||
There was a problem hiding this comment.
fix grammar, do not use too much or.
paddlespeech/t2s/exps/synthesize.py
Outdated
| parser.add_argument( | ||
| "--nxpu", | ||
| type=int, | ||
| default=0, | ||
| help="if wish to use xpu, set ngpu == 0 and nxpu > 0, and if ngpu == 0 and nxpu == 0, use cpu." | ||
| help="if wish to use xpu, set ngpu == 0 and nxpu > 0, and if ngpu == 0 and nxpu == 0 and nnpu == 0, use cpu." |
There was a problem hiding this comment.
help should be written more concisely
paddlespeech/t2s/exps/synthesize.py
Outdated
| "--nnpu", | ||
| type=int, | ||
| default=0, | ||
| help="if wish to use npu, set ngpu == 0 and nxpu == 0 and nnpu > 0, and if ngpu == 0 and nxpu == 0 and nnpu == 0, use cpu." |
paddlespeech/t2s/exps/syn_utils.py
Outdated
| @@ -591,7 +591,8 @@ def get_predictor( | |||
|
|
|||
| config = inference.Config( | |||
| str(Path(model_dir) / model_file), str(Path(model_dir) / params_file)) | |||
| config.enable_memory_optim() | |||
| if device != "npu": | |||
There was a problem hiding this comment.
need to check why can not support here.
zxcd
reviewed
Aug 20, 2024
| paddle.set_device("cpu") | ||
| else: | ||
| print("ngpu or nxpu should >= 0 !") | ||
| print("ngpu, nxpu and nnpu should be >= 0") |
zxcd
reviewed
Aug 20, 2024
| paddle.set_device("cpu") | ||
| else: | ||
| print("ngpu or nxpu should >= 0 !") | ||
| print("ngpu, nxpu and nnpu should be >= 0") |
zxcd
approved these changes
Aug 20, 2024
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
PR types
New features
PR changes
Others
Describe
SpeedySpeech code adaption for npu, add device support and training, synthesize, synthesize_e2e and inference scripts