(Noob question) ValueError: No phonemizer found for language de.

[ninoppp]

Hey
I've just spun up TTS locally in a python 3.9.7 venv on an ubuntu vm.
However, when trying to install the Thorsten model, I get ValueError: No phonemizer found for language de.
More specifically:
`(ThorstenVoice) user@pc:~/ThorstenVoice$ tts-server --model_name tts_models/de/thorsten/tacotron2-DCA

tts_models/de/thorsten/tacotron2-DCA is already downloaded.
vocoder_models/de/thorsten/fullband-melgan is already downloaded.
Using model: Tacotron2
Setting up Audio Processor...
| > sample_rate:22050
| > resample:False
| > num_mels:80
| > log_func:np.log10
| > min_level_db:-100
| > frame_shift_ms:None
| > frame_length_ms:None
| > ref_level_db:20
| > fft_size:1024
| > power:1.5
| > preemphasis:0.0
| > griffin_lim_iters:60
| > signal_norm:True
| > symmetric_norm:True
| > mel_fmin:50.0
| > mel_fmax:8000.0
| > pitch_fmin:0.0
| > pitch_fmax:640.0
| > spec_gain:1.0
| > stft_pad_mode:reflect
| > max_norm:4.0
| > clip_norm:True
| > do_trim_silence:True
| > trim_db:50
| > do_sound_norm:False
| > do_amp_to_db_linear:True
| > do_amp_to_db_mel:True
| > do_rms_norm:False
| > db_level:None
| > stats_path:/home/juan/.local/share/tts/tts_models--de--thorsten--tacotron2-DCA/scale_stats.npy
| > base:10
| > hop_length:256
| > win_length:1024
Traceback (most recent call last):
File "/home/juan/ThorstenVoice/lib/python3.9/site-packages/TTS/tts/utils/text/tokenizer.py", line 192, in init_from_config
DEF_LANG_TO_PHONEMIZER[config.phoneme_language], **phonemizer_kwargs
KeyError: 'de'

`The above exception was the direct cause of the following exception:

Traceback (most recent call last):
File "/home/juan/ThorstenVoice/bin/tts-server", line 5, in
from TTS.server.server import main
File "/home/juan/ThorstenVoice/lib/python3.9/site-packages/TTS/server/server.py", line 102, in
synthesizer = Synthesizer(
File "/home/juan/ThorstenVoice/lib/python3.9/site-packages/TTS/utils/synthesizer.py", line 76, in init
self._load_tts(tts_checkpoint, tts_config_path, use_cuda)
File "/home/juan/ThorstenVoice/lib/python3.9/site-packages/TTS/utils/synthesizer.py", line 113, in _load_tts
self.tts_model = setup_tts_model(config=self.tts_config)
File "/home/juan/ThorstenVoice/lib/python3.9/site-packages/TTS/tts/models/init.py", line 13, in setup_model
model = MyModel.init_from_config(config, samples)
File "/home/juan/ThorstenVoice/lib/python3.9/site-packages/TTS/tts/models/tacotron2.py", line 356, in init_from_config
tokenizer, new_config = TTSTokenizer.init_from_config(config)
File "/home/juan/ThorstenVoice/lib/python3.9/site-packages/TTS/tts/utils/text/tokenizer.py", line 195, in init_from_config
raise ValueError(
ValueError: No phonemizer found for language de.
You may need to install a third party library for this language.
`
This is probably a really stupid question, but how can I install said third party library? Thanks for any help.

[p0p4k]

gruut[cs,de,es,fr,it,nl,pt,ru,sv]~=2.0.0
Did you install requirements.txt?

[ninoppp]

I followed this guide, so I did pip install -U pip TTS
When installing the requirements.txt, everything is already satisfied.

[thorstenMueller]

This model has been trained on espeak or espeak-ng. Is this installed and available on your system? Maybe you can try pip install TTS==0.5.0 and give it another try.

[ninoppp]

@thorstenMueller installing espeak did the trick, thanks! Maybe it would be worth mentioning this requirement in the guide, for the ultra noobs like me :)

[erogol]

You need to install the backend you want to use. Espeak or Gruut.

For Espeak run sudo apt install espeak on Ubuntu. We can't distribute espeak with TTS due to license conflicts.