Skip to content

AttributeError: 'AttrDict' object has no attribute 'attention_type' OSX #387

@varungujjar

Description

@varungujjar

Hi hope to gets some help here.. been sweating on this since last 3 days still cant get to work

Am building the server whl file using the following platform
OS: OSX
Python version 3.7.1
Model Tacotron2-iter-260K
builds fine

Other Perfectly Running model servers : Tacotron 2 + Forward Attention + PWGAN

while running the model server 'Tacotron2-iter-260K'i get the following error
is there anything wrong that am doing ?

would be great if someone could help me here.. :(

python -m TTS.server.server

Loading TTS model ...
| > model config: /Volumes/Work/dev/text_to_speech/tts_env/lib/python3.7/site-packages/TTS/server/model/tts/config.json
| > checkpoint file: /Volumes/Work/dev/text_to_speech/tts_env/lib/python3.7/site-packages/TTS/server/model/tts/checkpoint.pth.tar
Setting up Audio Processor...
| > sample_rate:22050
| > num_mels:80
| > min_level_db:-100
| > frame_shift_ms:12.5
| > frame_length_ms:50
| > ref_level_db:20
| > num_freq:1025
| > power:1.5
| > preemphasis:0.98
| > griffin_lim_iters:60
| > signal_norm:True
| > symmetric_norm:False
| > mel_fmin:0
| > mel_fmax:8000.0
| > max_norm:1.0
| > clip_norm:True
| > do_trim_silence:True
| > trim_db:60
| > sound_norm:False
| > n_fft:2048
| > hop_length:275
| > win_length:1100
Using model: Tacotron2
Traceback (most recent call last):
File "/Library/Frameworks/Python.framework/Versions/3.7/lib/python3.7/runpy.py", line 193, in _run_module_as_main
"main", mod_spec)
File "/Library/Frameworks/Python.framework/Versions/3.7/lib/python3.7/runpy.py", line 85, in _run_code
exec(code, run_globals)
File "/Volumes/Work/dev/homie/text_to_speech/tts_env/lib/python3.7/site-packages/TTS/server/server.py", line 62, in
synthesizer = Synthesizer(args)
File "/Volumes/Work/dev/homie/text_to_speech/tts_env/lib/python3.7/site-packages/TTS/server/synthesizer.py", line 35, in init
self.config.use_cuda)
File "/Volumes/Work/dev/homie/text_to_speech/tts_env/lib/python3.7/site-packages/TTS/server/synthesizer.py", line 68, in load_tts
self.tts_model = setup_model(self.input_size, num_speakers=num_speakers, c=self.tts_config)
File "/Volumes/Work/dev/homie/text_to_speech/tts_env/lib/python3.7/site-packages/TTS/utils/generic_utils.py", line 311, in setup_model
attn_type=c.attention_type,
AttributeError: 'AttrDict' object has no attribute 'attention_type'

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions