Assamese model inferencing

[shreerakshaachlady]

Hi,
I am trying to infer on Assamese model in the shared link.Getting the issue in config file.Using the below command mentioned in the repo.

python3 -m TTS.bin.synthesize --text "কেনেকুৱা আছ? আজি আহিব নালাগে" --model_path as/fastpitch//best_model.pth --config_path as/fastpitch/config.json --vocoder_path as/hifigan/best_model.pth --vocoder_config_path as/hifigan/config.json --out_path ./

Getting the below issue:
symbols, phonemes = make_symbols(**self.tts_config.characters)
TypeError: make_symbols() got an unexpected keyword argument 'characters_class'

Seems like some extra keyword has come in config.I tried removing these but phoneme generation also has some error.

[D1neshRawat]

Hi Shree,
How Did you used assamese model ?
I am trying to use it in this way.
from TTS.TTS.api import TTS
import torch
import soundfile
print(TTS().list_models())
BASE_DIR = os.path.dirname(os.path.dirname(os.path.abspath(file)))

Initialize TTS model with custom path

model_path = "/Users/dineshrawat/1_Ethereal/Ethereal_Touch_Py/models/v1/as/fastpitch/best_model.pth"
config_path = "/Users/dineshrawat/1_Ethereal/Ethereal_Touch_Py/models/v1/as/fastpitch/config.json"
vocoder_path = "/Users/dineshrawat/1_Ethereal/Ethereal_Touch_Py/models/v1/as/hifigan/best_model.pth"
vocoder_config_path = "/Users/dineshrawat/1_Ethereal/Ethereal_Touch_Py/models/v1/as/hifigan/config.json"
tts = TTS(model_path=model_path,
config_path=config_path,
vocoder_path=vocoder_path,
vocoder_config_path=vocoder_config_path).to(device_id)
g
Getting two kinds of error

1. when using the TTS from coqui-ai it gives speaker id is not correct.
2. when using gokulkarthik tts lib i am not able to import the library and give error that.
   ModuleNotFoundError("No module named 'TTS.TTS.api'")