[Bug] --list_speaker_idxs flag return 'NoneType' object has no attribute 'speaker_ids'

[Wonder1905]

🐛 Description

I'm using this repo just for inference, hence this entire repo is only about inference.
I'm running the following command:
tts --model_name tts_models/en/ljspeech/glow-tts --vocoder_name vocoder_models/en/ek1/wavegrad --list_speaker_idxs
In order to see the least of speakers available, just as in the documentation, but I'm getting:

Available speaker ids: (Set --speaker_idx flag to one of these values to use the multi-speaker model.
Traceback (most recent call last):
File "/opt/conda/bin/tts", line 8, in
sys.exit(main())
File "/opt/conda/lib/python3.8/site-packages/TTS/bin/synthesize.py", line 264, in main
print(synthesizer.tts_model.speaker_manager.speaker_ids)
AttributeError: 'NoneType' object has no attribute 'speaker_ids'

** Non related question: can I output a wav file with 16000Hz and not 22050Hz?? using the command line.

Environment

The script's output.
{
"CUDA": {
"GPU": [
"NVIDIA GeForce GTX 1080 Ti",
"NVIDIA GeForce GTX 1080 Ti",
"NVIDIA GeForce GTX 1080 Ti",
"NVIDIA GeForce GTX 1080 Ti"
],
"available": true,
"version": "11.1"
},
"Packages": {
"PyTorch_debug": false,
"PyTorch_version": "1.8.1+cu111",
"TTS": "0.6.1",
"numpy": "1.19.5"
},
"System": {
"OS": "Linux",
"architecture": [
"64bit",
"ELF"
],
"processor": "x86_64",
"python": "3.8.5",
"version": "#1 SMP Tue Nov 30 15:51:32 UTC 2021"
}
}

Thanks a lot !!!

[p0p4k]

Is ljspeech multi-speaker dataset?

[erogol]

It's a single-speaker model.