GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
KEYHAN-A
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
KEYHAN-A
Model Tree
unsloth/orpheus-3b-0.1-ft-unsloth-bnb-4bit
Input Modalities
Output Modalities
Supported Functionality
bash
pip install torch transformers snac soundfile numpycurl -L https://raw.githubusercontent.com/KEYHAN-A/aava-refinement/main/examples/inference.py -o aava_inference.pypython aava_inference.py --text "سلام، من آوا هستم"
The script auto-selects CUDA, Apple MPS, or CPU and downloads
KEYHAN-A/aava-tts-persian-3b on first use.
| Architecture | LlamaForCausalLM + SNAC decoder |
| Parameters | ~3.78B |
| Precision | bfloat16 |
| Storage | ~7.59 GB, two safetensors shards |
| Context | 4,096 tokens |
| Codec / output | SNAC, mono 24 kHz |
| Language | Persian (fa) |
This model is the inference-oriented counterpart of the Aava LoRA adapter.
| Setting | Value |
|---|---|
| Training records | 492,596 |
| Tokenized corpus | ~1,905.3 hours |
| Method | LoRA, rank 128, alpha 256 |
| Epochs / steps | 3 / 184,725 |
| Effective batch | 8 |
| Learning rate | 1.5e-4 |
| Precision | bfloat16 |
| Reported eval loss | 4.2045 |
The ~2,400-hour raw-source total must not be confused with the refined training duration.
The training corpus contains 547,328 multi-source, multi-speaker Persian
records under one conditioning label (aava).
The reported eval loss is an internal training metric. Exact transcript duplicates cross the original sequential splits, so the metric is not a clean generalization benchmark.
The merged weights are Apache-2.0, following the direct Orpheus/Unsloth base. Orpheus is Apache-2.0 and SNAC is MIT licensed. No upstream endorsement is implied.
bibtex
@misc{aava_tts_merged_2026,title = {Aava TTS: Persian Orpheus 3B Merged Model},author = {{KEYHAN-A}},year = {2026},version = {1.0.0},url = {https://huggingface.co/KEYHAN-A/aava-tts-persian-3b}}