Downloads · 30 days
15
8% of all-time downloads
omersaidd/sesame_csm_nisan_kumru_turkish_4000_steps
sesame_csm_nisan_kumru_turkish_4000_steps is a text-to-audio model from omersaidd. Use it for the text-to-audio task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as mit.
<audio controls src="https://cdn-uploads.huggingface.co/production/uploads/65327bbe910b844786524e3c/1jK8UGgHG6FlfKsSz8ivd.mpga"</audio
Downloads · 30 days
15
8% of all-time downloads
All-time downloads
188
Public
Parameters
1.6B
6.6 GB on disk
Likes
1
Public
Click a slice to open those files.
.safetensors6.6 GB · 100%
How the weights are stored.
F321.6B · 99%
From the Hugging Face model README
from transformers import TrainingArguments, Trainer
from unsloth import is_bfloat16_supported
trainer = Trainer(
model = model,
train_dataset = processed_ds,
args = TrainingArguments(
per_device_train_batch_size = 2,
gradient_accumulation_steps = 4,
warmup_steps = 5,
max_steps = 4000,
learning_rate = 2e-4,
fp16 = not is_bfloat16_supported(),
bf16 = is_bfloat16_supported(),
logging_steps = 1,
optim = "adamw_8bit",
weight_decay = 0.001, # Turn this on if overfitting
lr_scheduler_type = "linear",
seed = 3407,
output_dir = "outputs",
report_to = "none", # Use TrackIO/WandB etc
),
)
<audio controls src="https://cdn-uploads.huggingface.co/production/uploads/65327bbe910b844786524e3c/1jK8UGgHG6FlfKsSz8ivd.mpga"></audio>
<audio controls src="https://cdn-uploads.huggingface.co/production/uploads/65327bbe910b844786524e3c/uHUVNjJKSoExPCNMWur0j.mpga"></audio>
<audio controls src="https://cdn-uploads.huggingface.co/production/uploads/65327bbe910b844786524e3c/JQ1HtK6Nx2eiWYd1jX3gh.mpga"></audio>
<audio controls src="https://cdn-uploads.huggingface.co/production/uploads/65327bbe910b844786524e3c/0rPJTxLFHvWHfTK1cMPfF.mpga"></audio>