You need to agree to share your Hugging Face information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Log in or Sign Up to review the conditions and access this model content.

GigaAM-Uzbek β€” v2 (gigaam-uzbek-v2.ckpt) and v1

Uzbek (Latin script) speech recognition: full fine-tunes of GigaAM multilingual_ctc (220M Conformer-CTC). Academic research release β€” every training source is listed above and cited below; the model inherits the most restrictive input license (non-commercial).

File Model Training data
gigaam-uzbek-v2.ckpt E8 (recommended) 776h gold + 357h filtered pseudo-labeled conversational speech (1,242h effective)
gigaam-uzbek-v1.ckpt E3 646h gold (UzbekVoice + Common Voice)

Results (WER %, greedy CTC, identical normalization)

Benchmark domain zero-shot 220M zero-shot 600M v1 (E3) v2 (E8)
UzbekVoice dev read 5.08 4.15 2.18 2.28
Common Voice uz test read 7.67 5.77 7.52 6.88
FLEURS uz test* read 10.47 7.52 11.55 8.71
USC test studio read 9.72 7.17 13.17 8.98
FeruzaSpeech test† audiobook/news 6.08 5.42 6.44 2.32
Spontaneous benchmark (rustam1221)‑ podcasts/interviews 16.65 15.87 23.40 13.66
Telegram voice messages (OvozifyLabs) conversational 22.53 20.45 30.75 23.93
Qashqadaryo dialect podcast (Fdev071) dialect 49.93 48.62 57.78 51.81

* 17% of FLEURS references (digit rows) excluded β€” no number expansion. † FeruzaSpeech train split (same single speaker) is in v2 training data; score reflects speaker familiarity by corpus design. ‑ Caveat: 63 of 310 benchmark references share 8-word n-grams with the pseudo-labeled pools (the benchmark's source podcasts also appear in the islomov YouTube pools); a leak-guarded retrain is in progress. All other test sets show 0% n-gram overlap with training data.

Training (v2 / E8)

Fresh fine-tune from multilingual_ctc: lr 5e-5, 6 epochs, batch 64, bf16-mixed, SpecAugment defaults, Common Voice Γ—3 upsampled, checkpoint by WER on a 4.4k-utterance mixed dev set. Pseudo-labels: Gemini transcripts kept only where multilingual_large_ctc greedy output agrees within CER ≀ 10% (yield: news 68%, IT 69%, Abduqayum 67%, Tashkent podcasts 32%). Hardware: 1Γ— NVIDIA B200, ~6.5h.

Normalization

Single normalizer for all training and reference text (source): NFC β†’ apostrophe unification (Κ» ΚΌ ’ β€˜ Β΄ … β†’ ') **before** punctuation stripping β†’ lowercase β†’ GigaAMnormalize_raw_text` β†’ charset {space, ', a–z}; Cyrillic sources transliterated (1995 Latin).

Usage

import gigaam
model = gigaam.load_model("gigaam-uzbek-v2.ckpt")
print(model.transcribe("audio.wav"))  # 16 kHz mono

Limitations

Latin output only; no digits (number expansion pending); dialect speech still ~50% WER; non-commercial (inherits CC-BY-NC from one pseudo-label source).

Code, experiment registry, full report: https://github.com/SamariddinS/uzbek-voice

Downloads last month
-
Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support

Datasets used to train SamariddinS/uzbek-voice