Multi-Speaker TTS[Bug]

[fra1993]

Describe the bug

Hi, I tried to run the command

tts --model_name "<language>/<dataset>/<model_name>" --list_speaker_idxs

with different models and I always got an error.

To Reproduce

Run following command (this happens also for other models)

tts --model_name "tts_models/en/ek1/tacotron2" --list_speaker_idxs

Expected behavior

No response

Logs

`Traceback (most recent call last):

  File "/usr/local/bin/tts", line 33, in <module>

    sys.exit(load_entry_point('TTS', 'console_scripts', 'tts')())

  File "/TTS/TTS/bin/synthesize.py", line 281, in main

    print(synthesizer.tts_model.speaker_manager.ids)

AttributeError: 'NoneType' object has no attribute 'ids`

Environment

"CUDA": {

        "GPU": [],

        "available": false,

        "version": "10.2"

    },

    "Packages": {

        "PyTorch_debug": false,

        "PyTorch_version": "1.10.1+cu102",

        "TTS": "0.6.2",

        "numpy": "1.19.5"

    },

    "System": {

        "OS": "Linux",

        "architecture": [

            "64bit",

            "ELF"

        "processor": "x86_64",

        "python": "3.6.9",

        "version": "#45-Ubuntu SMP Tue Mar 29 14:48:14 UTC 2022"

Additional context

No response

[kin0303]

Maybe dataset is not for multispeaker, you can try vctk dataset

[erogol]

You need a multispeaker model. I close this but reopen it if the problem is there with multispeaker models too.