#  Running Test Cases:
> pytest   # will run all test cases - including ones that require a gpu
> pytest  -m "not gpu"  # run test cases that can work with just cpu

# Download the models:
curl https://docs-assets.developer.apple.com/ml-research/models/mdm/flickr64/vis_model.pth --output vis_model_64x64.pth
curl https://docs-assets.developer.apple.com/ml-research/models/mdm/flickr256/vis_model.pth --output vis_model_256x256.pth
curl https://docs-assets.developer.apple.com/ml-research/models/mdm/flickr1024/vis_model.pth --output vis_model_1024x1024.pth

# Launch Web Demo:
torchrun --standalone --nproc_per_node=1  ml_mdm/clis/generate_sample.py --port 19999

accelerate launch train_flux_lora_deepspeed.py --config "train_configs/test_lora.yaml"

accelerate launch train_flux_deepspeed_controlnet.py --config "train_configs/test_canny_controlnet.yaml"

# Ensure you have latest Hugging face transformers
pip install git+https://github.com/huggingface/transformers

# to build a web UI demoinstall the following packages
pip install -r requirements_web_demo.txt

# run Gradio web UI
python demo/web_demo_audio.py

# Clone repository:
git clone https://github.com/TheMody/No-learning-rates-needed-Introducing-SALSA-Stable-Armijo-Line-Search-Adaptation.git

# Create & activate env:
conda env create -f environment.yml
conda activate sls3

# Install dependencies:
pip install pytorch numpy transformers datasets tensorflow-datasets wandb

# NOTE: custom optimizer is in \salsa\SaLSA.py,comparison version are in \salsa\adam_sls.py:
from salsa.SaLSA import SaLSA
self.optimizer = SaLSA(model.parameters())

# NOTE: typical pytorch forward pass needs to be changed to:
def closure(backwards = False):
    y_pred = model(x)
    loss = criterion(y_pred, y)
    if backwards: loss.backward()
    return loss
optimizer.zero_grad()
loss = optimizer.step(closure = closure)

# Clone repository and install dependences:
pip install git+https://github.com/huggingface/parler-tts.git

# Inference with random voice
import torch
from parler_tts import ParlerTTSForConditionalGeneration
from transformers import AutoTokenizer
import soundfile as sf

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

model = ParlerTTSForConditionalGeneration.from_pretrained("parler-tts/parler-tts-mini-v1").to(device)
tokenizer = AutoTokenizer.from_pretrained("parler-tts/parler-tts-mini-v1")

prompt = "Hey, how are you doing today?"
description = "A female speaker delivers a slightly expressive and animated speech with a moderate speed and pitch. The recording is of very high quality, with the speaker's voice sounding clear and very close up."

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()
sf.write("parler_tts_out.wav", audio_arr, model.config.sampling_rate)y