Edit model card

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)
Downloads last month
4
Safetensors
Model size
647M params
Tensor type
FP16
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.