Cintin/parler-tts-mini-Jenny-colab

How to Get Started with the Model

Use the code below to get started with the model.

!pip install git+https://github.com/huggingface/parler-tts.git

Quick Start

from parler_tts import ParlerTTSForConditionalGeneration
from transformers import AutoTokenizer
import torch

device = "cuda:0" if torch.cuda.is_available() else "cpu"

# model = ParlerTTSForConditionalGeneration.from_pretrained("/kaggle/working/parler-tts/output_dir_training", torch_dtype=torch.float16).to(device)
# tokenizer = AutoTokenizer.from_pretrained("parler-tts/parler_tts_mini_v0.1")

model = ParlerTTSForConditionalGeneration.from_pretrained("Cintin/parler-tts-mini-Jenny-colab").to(device)
tokenizer = AutoTokenizer.from_pretrained("Cintin/parler-tts-mini-Jenny-colab")

prompt = "Hey, how are you doing today?"
description = "'Jenny delivers her words quite expressively, in a very confined sounding environment with clear audio quality. She speaks fast.'"

input_ids = tokenizer(description, return_tensors="pt").input_ids.to(device)
prompt_input_ids = tokenizer(prompt, return_tensors="pt").input_ids.to(device)

generation = model.generate(input_ids=input_ids, prompt_input_ids=prompt_input_ids)
audio_arr = generation.cpu().numpy().squeeze()

To play the audio

from IPython.display import Audio
Audio(audio_arr, rate=model.config.sampling_rate)