Instructions to use Anthropic-ai/Aiaudiotranslate with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Anthropic-ai/Aiaudiotranslate with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Anthropic-ai/Aiaudiotranslate",
	filename="claude-oss-f16.gguf",
)

llm.create_chat_completion(
	messages = "\"Меня зовут Вольфганг и я живу в Берлине\""
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use Anthropic-ai/Aiaudiotranslate with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Anthropic-ai/Aiaudiotranslate:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf Anthropic-ai/Aiaudiotranslate:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Anthropic-ai/Aiaudiotranslate:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf Anthropic-ai/Aiaudiotranslate:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf Anthropic-ai/Aiaudiotranslate:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Anthropic-ai/Aiaudiotranslate:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf Anthropic-ai/Aiaudiotranslate:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Anthropic-ai/Aiaudiotranslate:Q4_K_M

Use Docker

docker model run hf.co/Anthropic-ai/Aiaudiotranslate:Q4_K_M

LM Studio
Jan
Ollama
How to use Anthropic-ai/Aiaudiotranslate with Ollama:
```
ollama run hf.co/Anthropic-ai/Aiaudiotranslate:Q4_K_M
```

Unsloth Studio new

How to use Anthropic-ai/Aiaudiotranslate with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for Anthropic-ai/Aiaudiotranslate to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for Anthropic-ai/Aiaudiotranslate to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Anthropic-ai/Aiaudiotranslate to start chatting

Pi new

How to use Anthropic-ai/Aiaudiotranslate with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf Anthropic-ai/Aiaudiotranslate:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "Anthropic-ai/Aiaudiotranslate:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use Anthropic-ai/Aiaudiotranslate with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf Anthropic-ai/Aiaudiotranslate:Q4_K_M

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default Anthropic-ai/Aiaudiotranslate:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use Anthropic-ai/Aiaudiotranslate with Docker Model Runner:
```
docker model run hf.co/Anthropic-ai/Aiaudiotranslate:Q4_K_M
```

Lemonade

How to use Anthropic-ai/Aiaudiotranslate with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Anthropic-ai/Aiaudiotranslate:Q4_K_M

Run and chat with the model

lemonade run user.Aiaudiotranslate-Q4_K_M

List all available models

lemonade list

🚀 Official Release: Claude Audio & Claude OSS 9B

Precision Transcription, Nuanced Translation, and Powerful Open-Source Conversations.

🎙️ Claude Audio: The Enhanced Experience

Standard translations often lose the "soul" of the speaker. aiaudiotranslate.space leverages Claude’s advanced linguistic modeling to ensure that every AI transcript and AI audio translation maintains the original intent, tone, and cultural nuance of the source material.

Contextual AI Transcript: identifies speakers and technical terminology with high fidelity.
Nuanced AI Translation: Powered by Claude, our engine understands idioms and professional jargon.
Seamless Integration: Designed for researchers, creators, and global teams.

🤖 Claude OSS 9B: Multilingual Assistant

Note: Claude OSS 9B is an independent open model project and not an official release by Anthropic.

Claude OSS 9B is a multilingual conversational language model designed to deliver a familiar, polished assistant experience with strong instruction-following and stable identity behavior.

📊 Model Overview

Architecture: Fine-tuned on Qwen3.5 9b.
Parameters: 9 Billion.
Language Support: 200+ languages.
Training Data: Curated mixture of ~200,000 rows from Hugging Face open-source datasets.

✨ Intended Use Cases

General Chat: Polished, identity-consistent assistant behavior.
Reasoning: Preservation of complex reasoning-oriented prompting.
Writing & Summarization: High-quality text generation across various styles.
Multilingual Interaction: Robust performance across hundreds of locales.
Lightweight Coding: Practical help for general-purpose development tasks.

🧠 Training & Benchmarks

The model was fine-tuned with a specific focus on instruction following and identity reinforcement. By combining high-quality assistant-style conversations with reasoning preservation data, Claude OSS 9B maintains a stable persona while handling complex queries.

Benchmark	Score (Based on Qwen3.5 9b)
MMLU-Pro	82.5%
GPQA Diamond	81.7%
Multilingual (MMMLU)	81.2%

🛠️ Quick Start (Transformers)

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

model_id = "your-username/claude"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype="auto", device_map="auto")

messages = [{"role": "user", "content": "Explain the concept of quantum entanglement in simple terms."}]
# ... standard inference loop ...
📜 Our Philosophy
We believe that language should not be a barrier to the exchange of ideas. Whether through Audio Translation or the Claude OSS ecosystem, our tools are built to be helpful, harmless, and honest companions in your communication toolkit.

Downloads last month: 5,706

Safetensors

Model size

9B params

Tensor type

BF16