Views
No views yet
mlprogram) export of the multilingual_ctc variant of
ai-sage/GigaAM-Multilingual —
a 220M-parameter Conformer encoder with a charwise CTC head for Russian,
English, Kazakh, Kyrgyz, and Uzbek speech recognition. Runs fully on-device on
Apple Silicon, no Python at inference time.predict() per 30 s
window returns CTC log-probabilities; greedy decoding is a few lines on the
host. The mel front-end stays outside Core ML. The model emits plain lowercase
text without punctuation (charwise vocabulary of 70 characters + blank).| file | size | role |
|---|---|---|
GigaAMMultilingualCTC.mlpackage | 422 MB | Conformer encoder + CTC head, fixed 30 s window |
tokens.json | 392 B | 70 characters (space, apostrophe, a–z, Cyrillic incl. Central-Asian extensions) |
model_info.json | — | dims, blank id, languages, mel parameters, subsampling factor |
convert_info.json | — | window length in mel frames and encoder frames |
features float32 [1, 64, 2999] (log-mel, 30 s window, zero-padded
right), length int32 [1] (true mel frames). Output: log_probs float32
[1, 750, 71]. blank_id = 70; the 70 non-blank ids index tokens.json.enc_len = (true_mel_frames - 1) // 4 + 1n_fft = 320,
win_length = 320, hop_length = 160, center = False, 64 mel bins, HTK mel
scale, no filterbank norm, then log(clamp(x, 1e-9, 1e9)). No mean/variance
normalization. Frames for n samples = (n - 320) // 160 + 1.gigaam package) on Russian
and English samples decoded over the same padded 30 s window, at
CPU_AND_GPU compute units; mean |Δlog_probs| ≈ 0.006–0.008.torch.jit.trace(strict=False) → coremltools 9.0
(mlprogram, FLOAT16, macOS15). Source checkpoint:
multilingual_ctc.ckpt from the official Sber CDN (MD5
5379d887c53ccd9cb95981e2a1832720, as pinned by the gigaam package). The
three-package RNNT conversion recipe by smkrv
documented the rotary warm-up and fp16 length pitfalls this export follows.