Search results

Verify evals on Papers with Code

community-request

Status: Open.

#16156 In NVIDIA-NeMo/Speech;

· NielsRogge opened on Aug 28, 2026

Abnormal Punctuation and Excessive Sentence Segmentation in German (canary-180m-flash)

bugSomething isn't workingSomething isn't working

community-request

Status: Open.

#16154 In NVIDIA-NeMo/Speech;

· Ranger2000 opened on Aug 27, 2026

EncDecHybridRNNTCTCBPEEOUModel.validation_pass raises UnboundLocalError: text_pred on its default path

community-request

Status: Open.

#16150 In NVIDIA-NeMo/Speech;

· udsy19 opened on Aug 27, 2026

Relax the lightning<=2.4.0 constraint for NeMo Speech ASR

Status: Open.

#16144 In NVIDIA-NeMo/Speech;

· sarahyurick opened on Aug 26, 2026

[Nemotron VoiceChat] ASR EOS loss-weight mismatch between labels and token weighting

bugSomething isn't workingSomething isn't working

community-request

waiting-on-maintainersWaiting on maintainers to respondWaiting on maintainers to respond

Status: Open.

#16142 In NVIDIA-NeMo/Speech;

· petrichor20211 opened on Aug 26, 2026

Enable FP16/BF16 compute_dtype for cache-aware streaming ASR inference

bugSomething isn't workingSomething isn't working

community-request

waiting-on-maintainersWaiting on maintainers to respondWaiting on maintainers to respond

Status: Open.

#16137 In NVIDIA-NeMo/Speech;

· AdityaBiranje opened on Aug 25, 2026

Question: text-token bottleneck vs direct S2S in NemotronLabs VoiceChat

community-request

waiting-on-maintainersWaiting on maintainers to respondWaiting on maintainers to respond

Status: Open.

#16136 In NVIDIA-NeMo/Speech;

· saberya opened on Aug 25, 2026

S2S model with multi stage train

community-request

waiting-on-maintainersWaiting on maintainers to respondWaiting on maintainers to respond

Status: Open.

#16134 In NVIDIA-NeMo/Speech;

· saberya opened on Aug 25, 2026

BoostingTreeModelConfig.use_triton defaults to True, so GPU-PB via key_phrases_* crashes on CUDA when Triton is missing

community-request

waiting-on-maintainersWaiting on maintainers to respondWaiting on maintainers to respond

Status: Open.

#16122 In NVIDIA-NeMo/Speech;

· rips4w opened on Aug 20, 2026

Nemotron Labs VoiceChat image for streaming interaction

community-request

waiting-on-maintainersWaiting on maintainers to respondWaiting on maintainers to respond

Status: Open.

#16118 In NVIDIA-NeMo/Speech;

· yangyyt opened on Aug 20, 2026

UnboundLocalError: storage_options when an EMA callback is present and save_last_n_optim_states >= 0

community-request

Status: Open.

#16111 In NVIDIA-NeMo/Speech;

· udsy19 opened on Aug 18, 2026

exp_manager S3 resume check runs on every rank because the guard ANDs two mutually exclusive URL schemes

community-request

Status: Open.

#16110 In NVIDIA-NeMo/Speech;

· udsy19 opened on Aug 18, 2026