Cannot synthesize with fine-tuned model · coqui-ai TTS - GitHub I could synthesize text with my own model after providing a speaker name that I got from running tts with list_speaker_idx parameter AND (what I forgot initialy) the --config_path So to get speaker name : tts --model_path "{modelDir}{checkpointName}" --config_path "{modelDir}config json" --list_language_idxs --list_speaker_idxs
Fine tuned coqui XTTS voice, how to use the model. pth? output_path = r"F:\VoiceCloning\TTS\MyVoice\output wav" tts tts_to_file(text=text, file_path=output_path) print(f"Audio file saved to {output_path}") This complains about AttributeError: 'TTS' object has no attribute 'is_multi_speaker'
TTS 0. 22. 0 documentation - Coqui import torch from TTS api import TTS # Get device device = "cuda" if torch cuda is_available else "cpu" # List available 🐸TTS models print (TTS () list_models ()) # Init TTS tts = TTS ("tts_models multilingual multi-dataset xtts_v2") to (device) # Run TTS # Since this model is multi-lingual voice cloning model, we must set the target
--speaker_wav leads to AttributeError: NoneType object has no . . . input: tts --text 'Hello world!' --out_path out out_1 wav --model_name tts_models en vctk sc-glow-tts --vocoder_name vocoder_models en vctk hifigan_v2 --speaker_wav 28 wav output error > tts_models en vctk sc-glow-tts is already download
AttributeError: NoneType object has no attribute astype I tried to find the code for the line where the error occurred # read image by cv2 or from lmdb # return: Numpy float32, HWC, BGR, [0,1] if env is None: # img img = cv2 imread(path, cv2 IMREAD_UNCHANGED) else: img = _read_lmdb_img(env, path) img = img astype(np float32) 255 if img ndim == 2: img = np expand_dims(img, axis=2)
[Bug] AttributeError: NoneType object has no attribute load_wav . . . Describe the bug Fix #3108 breaks tts_with_vc_to_file at least with VITS See: TTS TTS api py Line 463 in 6fef4f9 self tts_to_file(text=text, speaker=None, language=language, file_path=fp name,speaker_wav=speaker_wav) By changing the lin