How do I make my model able to read a number?

[kin0303]

I tried to do multilingual training with the VITS model, I used Indonesian and English. But in the English model, when I make an inference, the model can't read the numbers. What do I need to do so that the model I'm training can read numbers?

When reading numbers using the English model it will produce output like this:

tts --text "Development version of eSpeak NG supports 127 languages and accents, which are listed in table below." --model_path /Coqui/TTS/VITS_Multi-February-10-2023_03+18PM-914280a5/checkpoint_300000.pth --config_path /Coqui/TTS/VITS_Multi-February-10-2023_03+18PM-914280a5/config.json --out_path /Audio/13-Februari-2023/1Coba_EN.wav --speaker_idx Male --language_idx en
 > Using model: vits
 > Setting up Audio Processor...
 | > sample_rate:22050
 | > resample:False
 | > num_mels:80
 | > log_func:np.log10
 | > min_level_db:0
 | > frame_shift_ms:None
 | > frame_length_ms:None
 | > ref_level_db:None
 | > fft_size:1024
 | > power:None
 | > preemphasis:0.0
 | > griffin_lim_iters:None
 | > signal_norm:None
 | > symmetric_norm:None
 | > mel_fmin:0
 | > mel_fmax:None
 | > pitch_fmin:None
 | > pitch_fmax:None
 | > spec_gain:20.0
 | > stft_pad_mode:reflect
 | > max_norm:1.0
 | > clip_norm:True
 | > do_trim_silence:False
 | > trim_db:60
 | > 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:None
 | > base:10
 | > hop_length:256
 | > win_length:1024
 > initialization of speaker-embedding layers.
 > initialization of language-embedding layers.
 > Text: Development version of eSpeak NG supports 127 languages and accents, which are listed in table below.
 > Text splitted to sentences.
['Development version of eSpeak NG supports 127 languages and accents, which are listed in table below.']
['<BLNK>', 'd', '<BLNK>', 'e', '<BLNK>', 'v', '<BLNK>', 'e', '<BLNK>', 'l', '<BLNK>', 'o', '<BLNK>', 'p', '<BLNK>', 'm', '<BLNK>', 'e', '<BLNK>', 'n', '<BLNK>', 't', '<BLNK>', ' ', '<BLNK>', 'v', '<BLNK>', 'e', '<BLNK>', 'r', '<BLNK>', 's', '<BLNK>', 'i', '<BLNK>', 'o', '<BLNK>', 'n', '<BLNK>', ' ', '<BLNK>', 'o', '<BLNK>', 'f', '<BLNK>', ' ', '<BLNK>', 'e', '<BLNK>', 's', '<BLNK>', 'p', '<BLNK>', 'e', '<BLNK>', 'a', '<BLNK>', 'k', '<BLNK>', ' ', '<BLNK>', 'n', '<BLNK>', 'g', '<BLNK>', ' ', '<BLNK>', 's', '<BLNK>', 'u', '<BLNK>', 'p', '<BLNK>', 'p', '<BLNK>', 'o', '<BLNK>', 'r', '<BLNK>', 't', '<BLNK>', 's', '<BLNK>', ' ', '<BLNK>', '1', '<BLNK>', '2', '<BLNK>', '7', '<BLNK>', ' ', '<BLNK>', 'l', '<BLNK>', 'a', '<BLNK>', 'n', '<BLNK>', 'g', '<BLNK>', 'u', '<BLNK>', 'a', '<BLNK>', 'g', '<BLNK>', 'e', '<BLNK>', 's', '<BLNK>', ' ', '<BLNK>', 'a', '<BLNK>', 'n', '<BLNK>', 'd', '<BLNK>', ' ', '<BLNK>', 'a', '<BLNK>', 'c', '<BLNK>', 'c', '<BLNK>', 'e', '<BLNK>', 'n', '<BLNK>', 't', '<BLNK>', 's', '<BLNK>', ',', '<BLNK>', ' ', '<BLNK>', 'w', '<BLNK>', 'h', '<BLNK>', 'i', '<BLNK>', 'c', '<BLNK>', 'h', '<BLNK>', ' ', '<BLNK>', 'a', '<BLNK>', 'r', '<BLNK>', 'e', '<BLNK>', ' ', '<BLNK>', 'l', '<BLNK>', 'i', '<BLNK>', 's', '<BLNK>', 't', '<BLNK>', 'e', '<BLNK>', 'd', '<BLNK>', ' ', '<BLNK>', 'i', '<BLNK>', 'n', '<BLNK>', ' ', '<BLNK>', 't', '<BLNK>', 'a', '<BLNK>', 'b', '<BLNK>', 'l', '<BLNK>', 'e', '<BLNK>', ' ', '<BLNK>', 'b', '<BLNK>', 'e', '<BLNK>', 'l', '<BLNK>', 'o', '<BLNK>', 'w', '<BLNK>', '.', '<BLNK>']
 [!] Character '1' not found in the vocabulary. Discarding it.
['<BLNK>', 'd', '<BLNK>', 'e', '<BLNK>', 'v', '<BLNK>', 'e', '<BLNK>', 'l', '<BLNK>', 'o', '<BLNK>', 'p', '<BLNK>', 'm', '<BLNK>', 'e', '<BLNK>', 'n', '<BLNK>', 't', '<BLNK>', ' ', '<BLNK>', 'v', '<BLNK>', 'e', '<BLNK>', 'r', '<BLNK>', 's', '<BLNK>', 'i', '<BLNK>', 'o', '<BLNK>', 'n', '<BLNK>', ' ', '<BLNK>', 'o', '<BLNK>', 'f', '<BLNK>', ' ', '<BLNK>', 'e', '<BLNK>', 's', '<BLNK>', 'p', '<BLNK>', 'e', '<BLNK>', 'a', '<BLNK>', 'k', '<BLNK>', ' ', '<BLNK>', 'n', '<BLNK>', 'g', '<BLNK>', ' ', '<BLNK>', 's', '<BLNK>', 'u', '<BLNK>', 'p', '<BLNK>', 'p', '<BLNK>', 'o', '<BLNK>', 'r', '<BLNK>', 't', '<BLNK>', 's', '<BLNK>', ' ', '<BLNK>', '1', '<BLNK>', '2', '<BLNK>', '7', '<BLNK>', ' ', '<BLNK>', 'l', '<BLNK>', 'a', '<BLNK>', 'n', '<BLNK>', 'g', '<BLNK>', 'u', '<BLNK>', 'a', '<BLNK>', 'g', '<BLNK>', 'e', '<BLNK>', 's', '<BLNK>', ' ', '<BLNK>', 'a', '<BLNK>', 'n', '<BLNK>', 'd', '<BLNK>', ' ', '<BLNK>', 'a', '<BLNK>', 'c', '<BLNK>', 'c', '<BLNK>', 'e', '<BLNK>', 'n', '<BLNK>', 't', '<BLNK>', 's', '<BLNK>', ',', '<BLNK>', ' ', '<BLNK>', 'w', '<BLNK>', 'h', '<BLNK>', 'i', '<BLNK>', 'c', '<BLNK>', 'h', '<BLNK>', ' ', '<BLNK>', 'a', '<BLNK>', 'r', '<BLNK>', 'e', '<BLNK>', ' ', '<BLNK>', 'l', '<BLNK>', 'i', '<BLNK>', 's', '<BLNK>', 't', '<BLNK>', 'e', '<BLNK>', 'd', '<BLNK>', ' ', '<BLNK>', 'i', '<BLNK>', 'n', '<BLNK>', ' ', '<BLNK>', 't', '<BLNK>', 'a', '<BLNK>', 'b', '<BLNK>', 'l', '<BLNK>', 'e', '<BLNK>', ' ', '<BLNK>', 'b', '<BLNK>', 'e', '<BLNK>', 'l', '<BLNK>', 'o', '<BLNK>', 'w', '<BLNK>', '.', '<BLNK>']
 [!] Character '2' not found in the vocabulary. Discarding it.
['<BLNK>', 'd', '<BLNK>', 'e', '<BLNK>', 'v', '<BLNK>', 'e', '<BLNK>', 'l', '<BLNK>', 'o', '<BLNK>', 'p', '<BLNK>', 'm', '<BLNK>', 'e', '<BLNK>', 'n', '<BLNK>', 't', '<BLNK>', ' ', '<BLNK>', 'v', '<BLNK>', 'e', '<BLNK>', 'r', '<BLNK>', 's', '<BLNK>', 'i', '<BLNK>', 'o', '<BLNK>', 'n', '<BLNK>', ' ', '<BLNK>', 'o', '<BLNK>', 'f', '<BLNK>', ' ', '<BLNK>', 'e', '<BLNK>', 's', '<BLNK>', 'p', '<BLNK>', 'e', '<BLNK>', 'a', '<BLNK>', 'k', '<BLNK>', ' ', '<BLNK>', 'n', '<BLNK>', 'g', '<BLNK>', ' ', '<BLNK>', 's', '<BLNK>', 'u', '<BLNK>', 'p', '<BLNK>', 'p', '<BLNK>', 'o', '<BLNK>', 'r', '<BLNK>', 't', '<BLNK>', 's', '<BLNK>', ' ', '<BLNK>', '1', '<BLNK>', '2', '<BLNK>', '7', '<BLNK>', ' ', '<BLNK>', 'l', '<BLNK>', 'a', '<BLNK>', 'n', '<BLNK>', 'g', '<BLNK>', 'u', '<BLNK>', 'a', '<BLNK>', 'g', '<BLNK>', 'e', '<BLNK>', 's', '<BLNK>', ' ', '<BLNK>', 'a', '<BLNK>', 'n', '<BLNK>', 'd', '<BLNK>', ' ', '<BLNK>', 'a', '<BLNK>', 'c', '<BLNK>', 'c', '<BLNK>', 'e', '<BLNK>', 'n', '<BLNK>', 't', '<BLNK>', 's', '<BLNK>', ',', '<BLNK>', ' ', '<BLNK>', 'w', '<BLNK>', 'h', '<BLNK>', 'i', '<BLNK>', 'c', '<BLNK>', 'h', '<BLNK>', ' ', '<BLNK>', 'a', '<BLNK>', 'r', '<BLNK>', 'e', '<BLNK>', ' ', '<BLNK>', 'l', '<BLNK>', 'i', '<BLNK>', 's', '<BLNK>', 't', '<BLNK>', 'e', '<BLNK>', 'd', '<BLNK>', ' ', '<BLNK>', 'i', '<BLNK>', 'n', '<BLNK>', ' ', '<BLNK>', 't', '<BLNK>', 'a', '<BLNK>', 'b', '<BLNK>', 'l', '<BLNK>', 'e', '<BLNK>', ' ', '<BLNK>', 'b', '<BLNK>', 'e', '<BLNK>', 'l', '<BLNK>', 'o', '<BLNK>', 'w', '<BLNK>', '.', '<BLNK>']
 [!] Character '7' not found in the vocabulary. Discarding it.
 > Processing time: 11.168020248413086
 > Real-time factor: 1.8896166856776286
 > Saving output to /Audio/13-Februari-2023/1Coba_EN.wav

[erogol]

You need to normalize them to text.

[kin0303]

You need to normalize them to text.

Thanks for the reply @erogol, but I managed to get it done yesterday.

And I have a new question. How do I get my model to read words in capital letters. I mean like TTS will read T T S or IoT will read I o T. Something like that

[ianujkr]

I am also facing the same issue, can u tell me how did u solved it?