Instructions to use Relbins/MongolianTTS_elevenlabs_v6 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Relbins/MongolianTTS_elevenlabs_v6 with Transformers:

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

pipe = pipeline("text-generation", model="Relbins/MongolianTTS_elevenlabs_v6")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Relbins/MongolianTTS_elevenlabs_v6")
model = AutoModelForCausalLM.from_pretrained("Relbins/MongolianTTS_elevenlabs_v6", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Relbins/MongolianTTS_elevenlabs_v6 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Relbins/MongolianTTS_elevenlabs_v6"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Relbins/MongolianTTS_elevenlabs_v6",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Relbins/MongolianTTS_elevenlabs_v6

SGLang

How to use Relbins/MongolianTTS_elevenlabs_v6 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 "Relbins/MongolianTTS_elevenlabs_v6" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Relbins/MongolianTTS_elevenlabs_v6",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "Relbins/MongolianTTS_elevenlabs_v6" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Relbins/MongolianTTS_elevenlabs_v6",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Relbins/MongolianTTS_elevenlabs_v6 with Docker Model Runner:
```
docker model run hf.co/Relbins/MongolianTTS_elevenlabs_v6
```

Uploaded model

Developed by: Dorjzodovsuren
License: apache-2.0

Description

Монгол хэлээр: Хамгийн сүүлийн үеийн дэвшилтэт арга техникийг ашиглан, бид ElevenLabs-ийн Монгол TTS (Text-to-Speech)-ийн чанарыг маш бага зардал, өндөр хурдтайгаар амжилттай бүтээж чадлаа. Ярианы байгалийн (naturalness) шинж чанарын хувьд анхны загвартайгаа тун ойрхон очсон бөгөөд энэхүү сургалтын үйл явцад ашигласан бүх өгөгдөл нь нийлэг (synthetic) өгөгдөл болно.

English: By utilizing the latest techniques, we have successfully trained ElevenLabs quality Mongolian TTS with remarkable cost-efficiency and speed. In terms of naturalness, it is quite close to the original, and all the training data used in this process was entirely synthetic.

Downloads last month: 99

Safetensors

Model size

3B params

Tensor type

BF16

Duplicated from Dorjzodovsuren/MongolianTTS_elevenlabs_v6

Relbins
/

MongolianTTS_elevenlabs_v6

Uploaded model

Description

Space using Relbins/MongolianTTS_elevenlabs_v6 1