diff --git a/examples/outetts/readme.md b/examples/outetts/readme.md index 29a230e4a..01c2b878d 100644 --- a/examples/outetts/readme.md +++ b/examples/outetts/readme.md @@ -15,7 +15,7 @@ However, it can be slightly challenging to set it up. You can also create your own cloned speaker voice. To do that, you will need Python 3.10+ with the `outetts` package installed. You can install it with this commands: ``` -pip install outetts --no-deps +pip install outetts==0.3.3 --no-deps pip install scipy einops pyyaml huggingface-hub encodec matplotlib transformers pytorch-lightning tensorboardX soundfile numpy jsonargparse torchcrepe librosa inflect loguru polars natsort tqdm sounddevice mecab-python3 unidic-lite uroman openai-whisper pygame accelerate ``` Then after that, obtain a wav file containing a sample of the voice you want to clone. diff --git a/examples/outetts/voice_cloning.py b/examples/outetts/voice_cloning.py index 804eacc33..522c8b2a1 100644 --- a/examples/outetts/voice_cloning.py +++ b/examples/outetts/voice_cloning.py @@ -9,7 +9,7 @@ model_config = outetts.HFModelConfig_v1( interface = outetts.InterfaceHF(model_version="0.2", cfg=model_config) speaker = interface.create_speaker( - audio_path="/path/to/audio.wav", + audio_path="input_audio.wav", # If transcript is not provided, it will be automatically transcribed using Whisper transcript=None, # Set to None to use Whisper for transcription