# Nemotron 3.5 Transcribe 30B-A4B, speech to text, on an RTX 5060 Ti 16 GB, runs of 29 Oct 2026.
# Placeholders:
#   <n>        index of the RTX 5060 Ti on its machine
#   <work>     the work folder: audio/, models/, NeMo-Speech.cpp/ (see environment.txt)
#   <runs>     the folder of the run, mounted writable as /w/runs/<label>
# Inside the container the work folder is /w. In the logs the runs are labelled e1 (run 1), e2 (run 2), r1 and r1b (whole hour),
# c1 and c2 (400 s pieces), d1 (piece 9 alone).

# One container per run, one GPU only, image built from the Dockerfile in scripts/ (see environment.txt):
docker run --rm --gpus '"device=<n>"' --user $(id -u):$(id -g) -e HOME=/tmp -v <work>:/w:ro -v <runs>:/w/runs/<label>:rw nemo-dev-2910:1 bash -c "<command>"

# The pieces of up to 2 minutes were cut once, before the runs, between utterances: scripts/make_chunks_short.py.txt <work>/audio 120 chunks120

# Run 1 and run 2 (<label> e1 and e2), the numbers on the page. The engine's 16 GB settings from the README of the quant, nothing lowered:
/w/NeMo-Speech.cpp/build/cuda-server/bin/nemo-speech transcribe /w/audio/chunks120 --model /w/models/NVIDIA-Nemotron-3.5-Transcribe-30B-A4B-AD-Q2_0_M.gguf --device cuda:0 -l en --format text --output-dir /w/runs/e2/out --concurrency 1 --asr.salm.max_sequences 2 --asr.salm.n_ctx_per_sequence 8192 --asr.salm.max_context 8192 --asr.salm.mtp_draft 0 --asr.salm.n_batch 512 --asr.salm.encoder_max_batch 2

# Whole hour in one request (<label> r1): the settings for one long request. It failed with out of memory.
/w/NeMo-Speech.cpp/build/cuda-server/bin/nemo-speech transcribe /w/audio/librispeech-test-clean-1h.wav --model /w/models/NVIDIA-Nemotron-3.5-Transcribe-30B-A4B-AD-Q2_0_M.gguf --device cuda:0 -l en --format text --output /w/runs/r1/out.txt --asr.salm.max_sequences 1 --asr.salm.n_ctx_per_sequence 73728 --asr.salm.max_context 73728 --asr.salm.mtp_draft 0 --asr.salm.n_batch 512 --asr.salm.encoder_max_batch 2 --asr.salm.encoder_ahead_seconds 1200

# Whole hour, second try (<label> r1b): the same, with smaller memory settings (n_batch 256, encoder_max_batch 1, encoder_ahead_seconds 120). It failed the same way.
/w/NeMo-Speech.cpp/build/cuda-server/bin/nemo-speech transcribe /w/audio/librispeech-test-clean-1h.wav --model /w/models/NVIDIA-Nemotron-3.5-Transcribe-30B-A4B-AD-Q2_0_M.gguf --device cuda:0 -l en --format text --output /w/runs/r1b/out.txt --asr.salm.max_sequences 1 --asr.salm.n_ctx_per_sequence 73728 --asr.salm.max_context 73728 --asr.salm.mtp_draft 0 --asr.salm.n_batch 256 --asr.salm.encoder_max_batch 1 --asr.salm.encoder_ahead_seconds 120

# Pieces of up to 400 s (<label> c1, repeated as c2): the same 16 GB settings as run 2, ten pieces.
/w/NeMo-Speech.cpp/build/cuda-server/bin/nemo-speech transcribe /w/audio/chunks --model /w/models/NVIDIA-Nemotron-3.5-Transcribe-30B-A4B-AD-Q2_0_M.gguf --device cuda:0 -l en --format text --output-dir /w/runs/c1/out --concurrency 1 --asr.salm.max_sequences 2 --asr.salm.n_ctx_per_sequence 8192 --asr.salm.max_context 8192 --asr.salm.mtp_draft 0 --asr.salm.n_batch 512 --asr.salm.encoder_max_batch 2

# Word error rate of run 1 and run 2 (<run> is run1 or run2). The 31 pieces of audio/chunks120.json are given with --chunk-list:
python wer.py --ref audio/reference-librispeech.txt --manifest audio/manifest.json --chunk-list audio/chunks120.json --hyp-chunks <run>/out --out wer.json --errors wer-errors.txt

# Word error rate of the 400 s pieces (limits/pieces-400s/out and limits/pieces-400s-repeat/out): the same line without --chunk-list, the ten pieces of audio/manifest.json are the default:
python wer.py --ref audio/reference-librispeech.txt --manifest audio/manifest.json --hyp-chunks <pieces folder>/out --out wer.json --errors wer-errors.txt