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
| Direct base | unsloth/orpheus-3b-0.1-ft-unsloth-bnb-4bit |
| Method | LoRA, rank 128, alpha 256, dropout 0.05 |
| Target modules | attention, MLP projections, embeddings |
| Context | 4,096 tokens |
| Audio codec | SNAC 24 kHz |
| Language | Persian (fa) |
| Adapter storage | ~1.77 GB |
python
import torchfrom peft import PeftModelfrom unsloth import FastLanguageModelmodel, tokenizer = FastLanguageModel.from_pretrained(model_name="unsloth/orpheus-3b-0.1-ft-unsloth-bnb-4bit",max_seq_length=4096,dtype=torch.bfloat16,load_in_4bit=True,)model = PeftModel.from_pretrained(model, "KEYHAN-A/aava-tts-persian")model.eval()
Generation produces Orpheus audio tokens that must be redistributed and decoded with SNAC. The complete reference implementation is in Aava Refinement.
| Setting | Value |
|---|---|
| Training records | 492,596 |
| Tokenized corpus | ~1,905.3 hours |
| Epochs / steps | 3 / 184,725 |
| Effective batch | 8 |
| Learning rate | 1.5e-4 |
| Scheduler | cosine with restarts |
| Optimizer | AdamW 8-bit |
| Precision | bfloat16 |
| Hardware | RTX 3090 24 GB |
The often-cited ~2,400-hour number is the raw acquisition duration, not the duration of the refined token corpus.
Training used 547,328 multi-source, multi-speaker Persian records under one
conditioning label, aava.
The reported evaluation loss is an internal training metric. A post-training audit found exact transcript duplication across the original sequential splits, so it must not be interpreted as a clean generalization benchmark.
The adapter weights are released under Apache-2.0, following the direct Orpheus/Unsloth base. Orpheus is Apache-2.0 and SNAC is MIT licensed. No endorsement by the upstream projects is implied.
bibtex
@misc{aava_tts_2026,title = {Aava TTS: Persian Orpheus 3B Adapter},author = {{KEYHAN-A}},year = {2026},version = {1.0.0},url = {https://huggingface.co/KEYHAN-A/aava-tts-persian}}
| Training time | ~11 days |
| Reported eval loss | 4.2045 |