GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
AK04-IXR
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
AK04-IXR
Model Tree
sarvamai/sarvam-1
Input Modalities
Output Modalities
Supported Functionality
On a held-out split it reproduces the espeak-ng reference with 0.00% PER / 100% exact phoneme match (n=60) — i.e. it generalizes the phonemizer's deterministic mapping to unseen sentences.
python
from peft import PeftModelfrom transformers import AutoModelForCausalLM, AutoTokenizer tok = AutoTokenizer.from_pretrained("sarvamai/sarvam-1")m = AutoModelForCausalLM.from_pretrained("sarvamai/sarvam-1")m = PeftModel.from_pretrained(m, "AK04-IXR/sarvam1-hinglish-g2p-lora") prompt = "Input: Mera flight ticket pee-en-aar eight three nine two hai.\nOutput:"ids = tok(prompt, return_tensors="pt").to(m.device)out = m.generate(**ids, max_new_tokens=160, do_sample=False)print(tok.decode(out[0][ids['input_ids'].shape[1]:], skip_special_tokens=True))LoRA (r=16, α=32; 0.94% of params) on ~7k (text → IPA) pairs phonemized by espeak-ng (en-us), 3 epochs, bf16, single A100.
Distilled from espeak-ng, so it matches (does not surpass) that reference; trained on Latin-script normalized text (Devanagari-carrier lines held out), and code-switched phonemization (per-span language ID) remains an open problem.