+ QV-j~^RIt^RIHtHt]P!]4t]!4'd^RItRRRlltRRlt R#)N)is_torchaudio_availableloggingcV^8dQhR\PR\PR\PR\PR\R\R\P/#)logitstargets logit_lengthstarget_lengthsblank_token_id reductionreturn)torchTensorintstr)formats"l/Volumes/fast/ai/experiments/ui-tars-smoke/.venv/lib/python3.14/site-packages/transformers/loss/loss_rnnt.py __annotate__rsb?? LL? \\?<<?LL ?  ?  ? \\?c 2\4'g \R4hR pWV9d)\RV RR PR V44 R 24hVP VP 4p\ PPVP4P4VP VP 4P4VP VP 4P4VP4VRR 7pVR8Xd4VP4VP4P4, #VR8XdVP4#VR8Xd%WsP4, P4#VR8XdVP4#V#)a Compute standard RNN-T (RNN Transducer) loss (https://huggingface.co/papers/1211.3711). Thin wrapper around [`torchaudio.functional.rnnt_loss`]. torchaudio is queried with `reduction="none"` to get the per-sample negative log-likelihoods, and the requested reduction is applied here. The reduction names and formulas mirror NeMo's `RNNTLoss` (the reference implementation used to train/finetune Parakeet), so that loss magnitudes and gradient scaling match when finetuning other RNNT models like Parakeet: - `"mean_volume"`: sum of per-sample losses divided by the sum of target lengths (per-token average over the whole batch). This is what `nvidia/parakeet-rnnt-0.6b` is trained with (`rnnt_reduction: mean_volume`). - `"mean_batch"`: plain average of per-sample losses over the batch (NeMo's default). - `"mean"`: per-sample loss divided by its own target length, then averaged over the batch. - `"sum"`: sum of per-sample losses. - `"none"`: per-sample losses, unreduced. Args: logits: Joint token logits of shape `(batch, T, U+1, vocab_size)`. targets: Target labels of shape `(batch, U)`. logit_lengths: Encoder output lengths of shape `(batch,)`. target_lengths: Target lengths of shape `(batch,)`. blank_token_id: Blank token id. reduction: Loss reduction method. One of `"mean_volume"`, `"mean_batch"`, `"mean"`, `"sum"`, or `"none"`. Returns: Scalar loss tensor (or per-example losses if `reduction="none"`). zWComputing the RNN-T loss requires torchaudio. Install it with `pip install torchaudio`. mean_volume mean_batchmeansumnonezInvalid reduction mode "z". Expected one of z, c38"TFp\V4xK R#5i)N)repr).0rs& r rnnt_loss..DsNq`p[\tTUww`ps.)rrr r blankr )rrrrr)r ImportError ValueErrorjointodevice torchaudio functional rnnt_lossfloat contiguousrrr)rrr r r r valid_reductionslossess&&&&&& rr+r+s^H # $ $sttK(&yk1DTYYNq`pNqEqDrrs t  $&&v}}5N  " " , ,||~((* 6==)--/#&&v}}599;%))+ -FM!zz|n22488::: l "{{} f --//5577 e zz| Mrc $\VVVVVVR7#))rrr r r r )r+)rlabelsr label_lengthsr r kwargss&&&&&&,rParakeetForRNNTLossr4\s# #$%  r)r) rutilsrr get_logger__name__loggerr)r+r4rrr:s6 4   H %?Dr