Vall-E Backend: AttributeError: 'Config' object has no attribute 'hdf5' #340
Labels
No Label
bug
duplicate
enhancement
help wanted
insufficient info
invalid
news
not a bug
question
wontfix
No Milestone
No project
No Assignees
2 Participants
Notifications
Due Date
No due date set.
Dependencies
No dependencies set.
Reference: mrq/ai-voice-cloning#340
Loading…
Reference in New Issue
Block a user
No description provided.
Delete Branch "%!s()"
Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?
The Vall-E backend crashes whenenver whenever I open ai-voice-cloning
./start.sh --tts-backend="vall-e" yaml="./training/valle/config.yaml"
`Whisper detected
Error while opening HDF5 file: ./training/valle/data.h5 [Errno 2] Unable to open file (unable to open file: name = './training/valle/data.h5', errno = 2, error message = 'No such file or directory', flags = 0, o_flags = 0)
VALL-E detected
Traceback (most recent call last):
File "/home/user/ai-voice-cloning/src/utils.py", line 105, in
import bark
ModuleNotFoundError: No module named 'bark'
Running on local URL: http://XXX.X.X.X:XXXX
To create a public link, set
share=True
inlaunch()
.Loading VALL-E... (Config: ./training//valle/config.yaml)
ar parameter count: 208996353
nar parameter count: 211091456
Traceback (most recent call last):
File "/home/user/ai-voice-cloning/./src/main.py", line 27, in
tts = load_tts()
File "/home/user/ai-voice-cloning/src/utils.py", line 3629, in load_tts
tts = VALLE_TTS(config=args.valle_model)
File "/home/user/ai-voice-cloning/modules/vall-e/vall_e/inference.py", line 57, in init
self.symmap = get_phone_symmap()
File "/home/user/ai-voice-cloning/modules/vall-e/vall_e/data.py", line 31, in get_phone_symmap
if cfg.dataset.use_hdf5 and 'symmap' in cfg.hdf5:
AttributeError: 'Config' object has no attribute 'hdf5'`
naruhodo
I forgot I have yet to actually test things without the
data.h5
dataset to supplement.If you want to conduct a bit of surgery in the meantime, go toIn./modules/vall-e/vall_e/data.py
at line 31 and 32, and comment them out / remove them../training/valle/config.yaml
, setdataset.use_hdf5
toFalse
.When I get a moment I'll fix it up to where
it can be ran without theit will disabledata.h5
dataset for the symmap table.use_hdf5
if it fails to load the file.