! python3 -m pip install -U phonemizer
! sudo apt install -y --no-install-recommends espeak-ng
import scipy, transformers
import torch
from diffusers import AudioLDM2Pipeline

repo_id = "anhnct/audioldm2_gigaspeech"
pipe = AudioLDM2Pipeline.from_pretrained(repo_id, torch_dtype=torch.float16)
pipe = pipe.to("cuda")

# define the prompts
prompt = "An female actor say with angry voice"
transcript = "wish you have a good day, i hope you never forget me"
negative_prompt = "low quality"

# run the generation
audio = pipe(
    prompt,
    negative_prompt=negative_prompt,
    transcription=transcript,
    num_inference_steps=200,
    audio_length_in_s=8.0,
    num_waveforms_per_prompt=1,
    max_new_tokens=512
).audios

# save the best audio sample (index 0) as a .wav file
scipy.io.wavfile.write("techno_2.wav", rate=16000, data=audio[0])
from IPython.display import Audio
Audio("techno_2.wav")