GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
Sanat-agrwl
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
Sanat-agrwl
Model Tree
Input Modalities
Output Modalities
Supported Functionality
bash
python word_timestamps.py clip.wav --model Sanat-agrwl/indic-whisper-ctc-timestamps --head ctc_head_E.ptOutputs the transcript followed by one line per word with start and end times in seconds.
Boundaries from a CTC head are systematically tight: words start about 38 ms late and end
about 100 ms early relative to human annotation. Subtracting those two constants roughly
halves the error, from 74.5 to 43.0 ms mean, measured out-of-sample against human boundaries.
Pass --calibrate to apply them. Because the offsets apply independently, calibrated spans of
adjacent words can overlap slightly.
The 20.8 ms above is agreement with an external wav2vec2 aligner, not accuracy. Measured against human annotation, this head and that aligner are statistically indistinguishable (74.5 vs 72.9 ms) yet agree with each other far more closely than either agrees with a person, because they share a systematic bias. Human inter-annotator agreement on the same task is 27.0 ms. See the annotations release and the paper.
Fine-tuned from vasista22/whisper-hindi-large-v2 (Apache-2.0), itself derived from OpenAI Whisper large-v2 (MIT), on IndicVoices-R (CC BY 4.0). Released under Apache-2.0; please attribute all three.
bibtex
@article{agrawal2026timestamped, title = {Timestamped Hindi speech transcription using Whisper}, author = {Agrawal, Sanat Kumar and Chetupalli, Srikanth Raj}, journal = {arXiv preprint arXiv:2610.08847}, year = {2026}}