Instructions to use Edcastro/poc1-vibevoice-model_Spanish_Italian with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Edcastro/poc1-vibevoice-model_Spanish_Italian with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("microsoft/VibeVoice-ASR")
model = PeftModel.from_pretrained(base_model, "Edcastro/poc1-vibevoice-model_Spanish_Italian")

Transformers

How to use Edcastro/poc1-vibevoice-model_Spanish_Italian with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="Edcastro/poc1-vibevoice-model_Spanish_Italian")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Edcastro/poc1-vibevoice-model_Spanish_Italian", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Edcastro/poc1-vibevoice-model_Spanish_Italian with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Edcastro/poc1-vibevoice-model_Spanish_Italian"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Edcastro/poc1-vibevoice-model_Spanish_Italian",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Edcastro/poc1-vibevoice-model_Spanish_Italian

SGLang

How to use Edcastro/poc1-vibevoice-model_Spanish_Italian with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "Edcastro/poc1-vibevoice-model_Spanish_Italian" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Edcastro/poc1-vibevoice-model_Spanish_Italian",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "Edcastro/poc1-vibevoice-model_Spanish_Italian" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Edcastro/poc1-vibevoice-model_Spanish_Italian",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Edcastro/poc1-vibevoice-model_Spanish_Italian with Docker Model Runner:
```
docker model run hf.co/Edcastro/poc1-vibevoice-model_Spanish_Italian
```

poc1-vibevoice-model_Spanish_Italian

This model is a fine-tuned version of microsoft/VibeVoice-ASR on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.0034

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 0.0001
train_batch_size: 4
eval_batch_size: 4
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 16
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.02
num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss
0.0185	1.5938	500	0.0039
0.0073	3.1852	1000	0.0037
0.0055	4.7789	1500	0.0034

Framework versions

PEFT 0.19.1
Transformers 4.51.3
Pytorch 2.5.1+cu121
Datasets 4.8.5
Tokenizers 0.21.4

Downloads last month: 4

Model tree for Edcastro/poc1-vibevoice-model_Spanish_Italian

Base model

microsoft/VibeVoice-ASR

Adapter

(8)

this model