nemo-parakeet-tdt-0.6b ASR model returns empty transcription #8682
Description
LocalAI version:
v3.12.1 (fcecc12), localai/localai:latest-gpu-intel docker image.
Environment, CPU architecture, OS, and Version:
Linux host 6.12.33-production+truenas #1 SMP PREEMPT_DYNAMIC Mon Feb 23 17:38:27 UTC 2026 x86_64 GNU/Linux
Describe the bug
nemo-parakeet-tdt-0.6b audio to text model fails to produce any output. When I send a request with sample audio, the text that gets returned is empty:
{"text":""}```
This does not happen with the `qwen3-asr-0.6b`:
```curl http://192.168.1.3:48080/v1/audio/transcriptions -H "Content-Type: multipart/form-data" -F file="@/home/alex/Downloads/samples_jfk.wav" -F model="qwen3-asr-0.6b"
{"segments":[{"id":0,"start":0,"end":0,"text":"And so, my fellow Americans, ask not what your country can do for you; ask what you can do for your country.","tokens":null}],"text":"And so, my fellow Americans, ask not what your country can do for you; ask what you can do for your country."}
To Reproduce
Send
curl http://192.168.1.3:48080/v1/audio/transcriptions -H "Content-Type: multipart/form-data" -F file="@/home/tannis/Downloads/samples_jfk.wav" -F model="nemo-parakeet-tdt-0.6b" (change the URL of the instance and point to the correct sample file location ofc)
Get
{"text":""}
Expected behavior
Get a transcription
Logs
CPU info:
model name : AMD Ryzen 7 3800X 8-Core Processor
flags : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx mmxext fxsr_opt pdpe1gb rdtscp lm constant_tsc rep_good nopl xtopology nonstop_tsc cpuid extd_apicid aperfmperf rapl pni pclmulqdq monitor ssse3 fma cx16 sse4_1 sse4_2 movbe popcnt aes xsave avx f16c rdrand lahf_lm cmp_legacy svm extapic cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw ibs skinit wdt tce topoext perfctr_core perfctr_nb bpext perfctr_llc mwaitx cpb cat_l3 cdp_l3 hw_pstate ssbd mba ibpb stibp vmmcall fsgsbase bmi1 avx2 smep bmi2 cqm rdt_a rdseed adx smap clflushopt clwb sha_ni xsaveopt xsavec xgetbv1 cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local clzero irperf xsaveerptr rdpru wbnoinvd arat npt lbrv svm_lock nrip_save tsc_scale vmcb_clean flushbyasid decodeassists pausefilter pfthreshold avic v_vmsave_vmload vgif v_spec_ctrl umip rdpid overflow_recov succor smca sev sev_es
CPU: AVX found OK
CPU: AVX2 found OK
CPU: no AVX512 found
Feb 28 19:52:46 DEBUG GPU vendor gpuVendor="" caller={caller.file="/build/pkg/system/state.go" caller.L=54 }
Feb 28 19:52:46 DEBUG Total available VRAM vram=0 caller={caller.file="/build/pkg/system/state.go" caller.L=56 }
Feb 28 19:52:46 INFO Using forced capability run file capabilityRunFile="/run/localai/capability" capability="intel\n" env="" caller={caller.file="/build/pkg/system/capabilities.go" caller.L=98 }
Feb 28 19:52:46 INFO Starting LocalAI threads=8 modelsPath="/models" caller={caller.file="/build/core/application/startup.go" caller.L=31 }
Feb 28 19:52:46 INFO LocalAI version version="v3.12.1 (fcecc12e57be39bad2ebf50cf729408b64409553)" caller={caller.file="/build/core/application/startup.go" caller.L=32 }
Feb 28 19:52:46 DEBUG agent_tasks.json not found, starting with empty tasks caller={caller.file="/build/core/services/agent_jobs.go" caller.L=129 }
Feb 28 19:52:46 DEBUG agent_jobs.json not found, starting with empty jobs caller={caller.file="/build/core/services/agent_jobs.go" caller.L=193 }
Feb 28 19:52:46 INFO AgentJobService started retention_days=30 caller={caller.file="/build/core/services/agent_jobs.go" caller.L=1347 }
Feb 28 19:52:46 DEBUG CPU capabilities capabilities=[3dnowprefetch abm adx aes aperfmperf apic arat avic avx avx2 bmi1 bmi2 bpext cat_l3 cdp_l3 clflush clflushopt clwb clzero cmov cmp_legacy constant_tsc cpb cpuid cqm cqm_llc cqm_mbm_local cqm_mbm_total cqm_occup_llc cr8_legacy cx16 cx8 de decodeassists extapic extd_apicid f16c flushbyasid fma fpu fsgsbase fxsr fxsr_opt ht hw_pstate ibpb ibs irperf lahf_lm lbrv lm mba mca mce misalignsse mmx mmxext monitor movbe msr mtrr mwaitx nonstop_tsc nopl npt nrip_save nx osvw overflow_recov pae pat pausefilter pclmulqdq pdpe1gb perfctr_core perfctr_llc perfctr_nb pfthreshold pge pni popcnt pse pse36 rapl rdpid rdpru rdrand rdseed rdt_a rdtscp rep_good sep sev sev_es sha_ni skinit smap smca smep ssbd sse sse2 sse4_1 sse4_2 sse4a ssse3 stibp succor svm svm_lock syscall tce topoext tsc tsc_scale umip v_spec_ctrl v_vmsave_vmload vgif vmcb_clean vme vmmcall wbnoinvd wdt xgetbv1 xsave xsavec xsaveerptr xsaveopt xtopology] caller={caller.file="/build/core/application/startup.go" caller.L=40 }
Feb 28 19:52:46 DEBUG No system backends found caller={caller.file="/build/core/gallery/backends.go" caller.L=335 }
Feb 28 19:52:46 DEBUG Registering backend name="qwen-asr" runFile="/backends/intel-qwen-asr/run.sh" caller={caller.file="/build/core/gallery/backends.go" caller.L=445 }
Feb 28 19:52:46 DEBUG Registering backend name="nemo" runFile="/backends/intel-nemo/run.sh" caller={caller.file="/build/core/gallery/backends.go" caller.L=445 }
Feb 28 19:52:46 DEBUG Registering backend name="intel-nemo" runFile="/backends/intel-nemo/run.sh" caller={caller.file="/build/core/gallery/backends.go" caller.L=445 }
Feb 28 19:52:46 DEBUG Registering backend name="intel-qwen-asr" runFile="/backends/intel-qwen-asr/run.sh" caller={caller.file="/build/core/gallery/backends.go" caller.L=445 }
Feb 28 19:52:46 INFO Preloading models path="/models" caller={caller.file="/build/core/config/model_config_loader.go" caller.L=269 }
Model name: nemo-parakeet-tdt-0.6b
Model name: qwen3-asr-0.6b
Feb 28 19:52:46 DEBUG Config overrides overrides=map[backend:nemo known_usecases:[transcript] parameters:map[model:nvidia/parakeet-tdt-0.6b-v3]] caller={caller.file="/build/core/gallery/models.go" caller.L=170 }
Feb 28 19:52:46 DEBUG Written config file file="/models/nemo-parakeet-tdt-0.6b.yaml" caller={caller.file="/build/core/gallery/models.go" caller.L=276 }
Feb 28 19:52:46 DEBUG Written gallery file file="/models/._gallery_nemo-parakeet-tdt-0.6b.yaml" caller={caller.file="/build/core/gallery/models.go" caller.L=286 }
Feb 28 19:52:46 DEBUG Installed model model="nemo-parakeet-tdt-0.6b" caller={caller.file="/build/core/gallery/models.go" caller.L=136 }
Feb 28 19:52:46 DEBUG Installing backend backend="nemo" caller={caller.file="/build/core/gallery/models.go" caller.L=138 }
Feb 28 19:52:46 DEBUG No system backends found caller={caller.file="/build/core/gallery/backends.go" caller.L=335 }
Feb 28 19:52:46 DEBUG Model name="nemo-parakeet-tdt-0.6b" config={/models/nemo-parakeet-tdt-0.6b.yaml {{nvidia/parakeet-tdt-0.6b-v3} false 0 0xc0003b6c80 0xc0003b6c88 0xc0003b6d40 0xc0003b6df0 false 0 false 0 0 0 0 0 0xc0003b6de8 0xc0003b6de0 0xc0003b6c28 {false} <nil> map[] 0 0 0 0 } nemo-parakeet-tdt-0.6b 0xc0003b6c68 0xc0003b6c60 0xc0003b6df8 map[] 0xc0003b6df9 nemo { false <nil> } [FLAG_TRANSCRIPT] 0xc0003b6e20 { } [] [] [] map[] {false {false false false false false false []} [] [] [] [] [] [] <nil>} {<nil> <nil> <nil> [] []} map[] { 0 0 false false 0xc0003b6dc8 0xc0003b6dc0 0xc0003b6d48 <nil> 0xc0003b6df8 0xc0003b6df9 0xc0003b6df9 0xc0003b6df9 [] [] [] [] [] 0xc0003b6e00 false [] [] 0 false 0 0 false false 0 0 0 false {0 0 0} <nil> false 0 0 0 0 0} {false false 0 } 0 {0 0} { } false [] [] [] { } {0 0 false false false false false 0 0 false}} caller={caller.file="/build/core/application/startup.go" caller.L=117 }
Feb 28 19:52:46 DEBUG Model name="qwen3-asr-0.6b" config={/models/qwen3-asr-0.6b.yaml {{Qwen/Qwen3-ASR-0.6B} false 0 0xc0003b7140 0xc0003b7148 0xc0003b7150 0xc0003b7190 false 0 false 0 0 0 0 0 0xc0003b7178 0xc0003b7170 0xc0003b7108 {false} <nil> map[] 0 0 0 0 } qwen3-asr-0.6b 0xc0003b7138 0xc0003b7130 0xc0003b7198 map[] 0xc0003b7199 qwen-asr { false <nil> } [FLAG_TRANSCRIPT] 0xc0003b71a8 { } [] [] [] map[] {false {false false false false false false []} [] [] [] [] [] [] <nil>} {<nil> <nil> <nil> [] []} map[] { 0 0 false false 0xc0003b7168 0xc0003b7160 0xc0003b7158 <nil> 0xc0003b7198 0xc0003b7199 0xc0003b7199 0xc0003b7199 [] [] [] [] [] 0xc0003b71a0 false [] [] 0 false 0 0 false false 0 0 0 false {0 0 0} <nil> false 0 0 0 0 0} {false false 0 } 0 {0 0} { } false [] [] [] { } {0 0 false false false false false 0 0 false}} caller={caller.file="/build/core/application/startup.go" caller.L=117 }
Feb 28 19:52:46 DEBUG runtime_settings.json not found, using defaults caller={caller.file="/build/core/application/startup.go" caller.L=214 }
Feb 28 19:52:46 DEBUG Auto loading model into memory from file model="nemo-parakeet-tdt-0.6b" file="nvidia/parakeet-tdt-0.6b-v3" caller={caller.file="/build/core/application/startup.go" caller.L=148 }
Feb 28 19:52:46 INFO BackendLoader starting modelID="nemo-parakeet-tdt-0.6b" backend="nemo" model="nvidia/parakeet-tdt-0.6b-v3" caller={caller.file="/build/pkg/model/initializers.go" caller.L=159 }
Feb 28 19:52:46 DEBUG Loading model in memory from file file="/models/nvidia/parakeet-tdt-0.6b-v3" caller={caller.file="/build/pkg/model/loader.go" caller.L=218 }
Feb 28 19:52:46 DEBUG Loading Model with gRPC modelID="nemo-parakeet-tdt-0.6b" file="/models/nvidia/parakeet-tdt-0.6b-v3" backend="nemo" options={nemo nvidia/parakeet-tdt-0.6b-v3 nemo-parakeet-tdt-0.6b {{}} 0xc0004dc908 map[] 20 2 false} caller={caller.file="/build/pkg/model/initializers.go" caller.L=53 }
Feb 28 19:52:46 DEBUG Loading external backend uri="/backends/intel-nemo/run.sh" caller={caller.file="/build/pkg/model/initializers.go" caller.L=77 }
Feb 28 19:52:46 DEBUG external backend is file file=&{run.sh 192 493 {0 63907278617 0x4f5f7e0} {1048702 132956 1 33261 0 0 0 0 192 512 9 {1771681817 0} {1771681817 0} {1772297206 809589494} [0 0 0]}} caller={caller.file="/build/pkg/model/initializers.go" caller.L=80 }
Feb 28 19:52:46 DEBUG Loading GRPC Process process="/backends/intel-nemo/run.sh" caller={caller.file="/build/pkg/model/process.go" caller.L=112 }
Feb 28 19:52:46 DEBUG GRPC Service will be running id="nemo-parakeet-tdt-0.6b" address="127.0.0.1:44879" caller={caller.file="/build/pkg/model/process.go" caller.L=114 }
Feb 28 19:52:46 DEBUG GRPC Service state dir dir="/tmp/go-processmanager2377681118" caller={caller.file="/build/pkg/model/process.go" caller.L=138 }
Feb 28 19:52:46 DEBUG GRPC Service Started caller={caller.file="/build/pkg/model/initializers.go" caller.L=92 }
Feb 28 19:52:46 DEBUG Wait for the service to start up caller={caller.file="/build/pkg/model/initializers.go" caller.L=105 }
Feb 28 19:52:46 DEBUG Options options=ContextSize:1024 Seed:216050458 NBatch:512 MMap:true NGPULayers:9999999 Threads:8 FlashAttention:"auto" caller={caller.file="/build/pkg/model/initializers.go" caller.L=106 }
Feb 28 19:52:46 DEBUG GRPC stdout id="nemo-parakeet-tdt-0.6b-127.0.0.1:44879" line="Initializing libbackend for intel-nemo" caller={caller.file="/build/pkg/model/process.go" caller.L=162 }
Feb 28 19:52:46 DEBUG GRPC stdout id="nemo-parakeet-tdt-0.6b-127.0.0.1:44879" line="Using portable Python" caller={caller.file="/build/pkg/model/process.go" caller.L=162 }
Feb 28 19:52:46 DEBUG GRPC stdout id="nemo-parakeet-tdt-0.6b-127.0.0.1:44879" line="Added /backends/intel-nemo/lib to LD_LIBRARY_PATH for GPU libraries" caller={caller.file="/build/pkg/model/process.go" caller.L=162 }
Feb 28 19:52:53 DEBUG GRPC stderr id="nemo-parakeet-tdt-0.6b-127.0.0.1:44879" line="/backends/intel-nemo/venv/lib/python3.10/site-packages/transformers/utils/hub.py:111: FutureWarning: Using `TRANSFORMERS_CACHE` is deprecated and will be removed in v5 of Transformers. Use `HF_HOME` instead." caller={caller.file="/build/pkg/model/process.go" caller.L=153 }
Feb 28 19:52:53 DEBUG GRPC stderr id="nemo-parakeet-tdt-0.6b-127.0.0.1:44879" line=" warnings.warn(" caller={caller.file="/build/pkg/model/process.go" caller.L=153 }
Feb 28 19:52:59 DEBUG GRPC stderr id="nemo-parakeet-tdt-0.6b-127.0.0.1:44879" line="[NeMo W 2026-02-28 19:52:59 megatron_init:62] Megatron num_microbatches_calculator not found, using Apex version." caller={caller.file="/build/pkg/model/process.go" caller.L=153 }
Feb 28 19:52:59 DEBUG GRPC stderr id="nemo-parakeet-tdt-0.6b-127.0.0.1:44879" line="OneLogger: Setting error_handling_strategy to DISABLE_QUIETLY_AND_REPORT_METRIC_ERROR for rank (rank=0) with OneLogger disabled. To override: explicitly set error_handling_strategy parameter." caller={caller.file="/build/pkg/model/process.go" caller.L=153 }
Feb 28 19:52:59 DEBUG GRPC stderr id="nemo-parakeet-tdt-0.6b-127.0.0.1:44879" line="No exporters were provided. This means that no telemetry data will be collected." caller={caller.file="/build/pkg/model/process.go" caller.L=153 }
Feb 28 19:53:02 DEBUG GRPC stderr id="nemo-parakeet-tdt-0.6b-127.0.0.1:44879" line="Server started. Listening on: 127.0.0.1:44879" caller={caller.file="/build/pkg/model/process.go" caller.L=153 }
Feb 28 19:53:04 DEBUG GRPC Service Ready caller={caller.file="/build/pkg/model/initializers.go" caller.L=113 }
Feb 28 19:53:04 DEBUG GRPC: Loading model with options options={{{} [] [] 0xc0007e1958} 0 [] nvidia/parakeet-tdt-0.6b-v3 1024 216050458 512 false false true false false false false 9999999 8 0 0 0 0 /models/nvidia/parakeet-tdt-0.6b-v3 false 0 false 0 0 false 0 false false 0 0 0 false 0 0 0 0 0 0 0 auto false /models [] [] [] [] false []} caller={caller.file="/build/pkg/model/initializers.go" caller.L=136 }
Feb 28 19:53:04 DEBUG GRPC stderr id="nemo-parakeet-tdt-0.6b-127.0.0.1:44879" line="Loading NEMO ASR model from nvidia/parakeet-tdt-0.6b-v3" caller={caller.file="/build/pkg/model/process.go" caller.L=153 }
Feb 28 19:53:11 DEBUG GRPC stdout id="nemo-parakeet-tdt-0.6b-127.0.0.1:44879" line="[NeMo I 2026-02-28 19:53:11 mixins:184] Tokenizer SentencePieceTokenizer initialized with 8192 tokens" caller={caller.file="/build/pkg/model/process.go" caller.L=162 }
Feb 28 19:53:15 DEBUG GRPC stderr id="nemo-parakeet-tdt-0.6b-127.0.0.1:44879" line="[NeMo W 2026-02-28 19:53:15 modelPT:188] If you intend to do training or fine-tuning, please call the ModelPT.setup_training_data() method and provide a valid configuration file to setup the train data loader." caller={caller.file="/build/pkg/model/process.go" caller.L=153 }
Feb 28 19:53:15 DEBUG GRPC stderr id="nemo-parakeet-tdt-0.6b-127.0.0.1:44879" line=" Train config : " caller={caller.file="/build/pkg/model/process.go" caller.L=153 }
Feb 28 19:53:15 DEBUG GRPC stderr id="nemo-parakeet-tdt-0.6b-127.0.0.1:44879" line=" use_lhotse: true" caller={caller.file="/build/pkg/model/process.go" caller.L=153 }
Feb 28 19:53:15 DEBUG GRPC stderr id="nemo-parakeet-tdt-0.6b-127.0.0.1:44879" line=" skip_missing_manifest_entries: true" caller={caller.file="/build/pkg/model/process.go" caller.L=153 }
Feb 28 19:53:15 DEBUG GRPC stderr id="nemo-parakeet-tdt-0.6b-127.0.0.1:44879" line=" input_cfg: null" caller={caller.file="/build/pkg/model/process.go" caller.L=153 }
Feb 28 19:53:15 DEBUG GRPC stderr id="nemo-parakeet-tdt-0.6b-127.0.0.1:44879" line=" tarred_audio_filepaths: null" caller={caller.file="/build/pkg/model/process.go" caller.L=153 }
Feb 28 19:53:15 DEBUG GRPC stderr id="nemo-parakeet-tdt-0.6b-127.0.0.1:44879" line=" manifest_filepath: null" caller={caller.file="/build/pkg/model/process.go" caller.L=153 }
Feb 28 19:53:15 DEBUG GRPC stderr id="nemo-parakeet-tdt-0.6b-127.0.0.1:44879" line=" sample_rate: 16000" caller={caller.file="/build/pkg/model/process.go" caller.L=153 }
Feb 28 19:53:15 DEBUG GRPC stderr id="nemo-parakeet-tdt-0.6b-127.0.0.1:44879" line=" shuffle: true" caller={caller.file="/build/pkg/model/process.go" caller.L=153 }
Feb 28 19:53:15 DEBUG GRPC stderr id="nemo-parakeet-tdt-0.6b-127.0.0.1:44879" line=" num_workers: 2" caller={caller.file="/build/pkg/model/process.go" caller.L=153 }
Feb 28 19:53:15 DEBUG GRPC stderr id="nemo-parakeet-tdt-0.6b-127.0.0.1:44879" line=" pin_memory: true" caller={caller.file="/build/pkg/model/process.go" caller.L=153 }
Feb 28 19:53:15 DEBUG GRPC stderr id="nemo-parakeet-tdt-0.6b-127.0.0.1:44879" line=" max_duration: 10.0" caller={caller.file="/build/pkg/model/process.go" caller.L=153 }
Feb 28 19:53:15 DEBUG GRPC stderr id="nemo-parakeet-tdt-0.6b-127.0.0.1:44879" line=" min_duration: 1.0" caller={caller.file="/build/pkg/model/process.go" caller.L=153 }
Feb 28 19:53:15 DEBUG GRPC stderr id="nemo-parakeet-tdt-0.6b-127.0.0.1:44879" line=" text_field: answer" caller={caller.file="/build/pkg/model/process.go" caller.L=153 }
Feb 28 19:53:15 DEBUG GRPC stderr id="nemo-parakeet-tdt-0.6b-127.0.0.1:44879" line=" batch_duration: null" caller={caller.file="/build/pkg/model/process.go" caller.L=153 }
Feb 28 19:53:15 DEBUG GRPC stderr id="nemo-parakeet-tdt-0.6b-127.0.0.1:44879" line=" max_tps: null" caller={caller.file="/build/pkg/model/process.go" caller.L=153 }
Feb 28 19:53:15 DEBUG GRPC stderr id="nemo-parakeet-tdt-0.6b-127.0.0.1:44879" line=" use_bucketing: true" caller={caller.file="/build/pkg/model/process.go" caller.L=153 }
Feb 28 19:53:15 DEBUG GRPC stderr id="nemo-parakeet-tdt-0.6b-127.0.0.1:44879" line=" bucket_duration_bins: null" caller={caller.file="/build/pkg/model/process.go" caller.L=153 }
Feb 28 19:53:15 DEBUG GRPC stderr id="nemo-parakeet-tdt-0.6b-127.0.0.1:44879" line=" bucket_batch_size: null" caller={caller.file="/build/pkg/model/process.go" caller.L=153 }
Feb 28 19:53:15 DEBUG GRPC stderr id="nemo-parakeet-tdt-0.6b-127.0.0.1:44879" line=" num_buckets: 30" caller={caller.file="/build/pkg/model/process.go" caller.L=153 }
Feb 28 19:53:15 DEBUG GRPC stderr id="nemo-parakeet-tdt-0.6b-127.0.0.1:44879" line=" bucket_buffer_size: 20000" caller={caller.file="/build/pkg/model/process.go" caller.L=153 }
Feb 28 19:53:15 DEBUG GRPC stderr id="nemo-parakeet-tdt-0.6b-127.0.0.1:44879" line=" shuffle_buffer_size: 10000" caller={caller.file="/build/pkg/model/process.go" caller.L=153 }
Feb 28 19:53:15 DEBUG GRPC stderr id="nemo-parakeet-tdt-0.6b-127.0.0.1:44879" line=" " caller={caller.file="/build/pkg/model/process.go" caller.L=153 }
Feb 28 19:53:15 DEBUG GRPC stderr id="nemo-parakeet-tdt-0.6b-127.0.0.1:44879" line="[NeMo W 2026-02-28 19:53:15 modelPT:195] If you intend to do validation, please call the ModelPT.setup_validation_data() or ModelPT.setup_multiple_validation_data() method and provide a valid configuration file to setup the validation data loader(s). " caller={caller.file="/build/pkg/model/process.go" caller.L=153 }
Feb 28 19:53:15 DEBUG GRPC stderr id="nemo-parakeet-tdt-0.6b-127.0.0.1:44879" line=" Validation config : " caller={caller.file="/build/pkg/model/process.go" caller.L=153 }
Feb 28 19:53:15 DEBUG GRPC stderr id="nemo-parakeet-tdt-0.6b-127.0.0.1:44879" line=" use_lhotse: true" caller={caller.file="/build/pkg/model/process.go" caller.L=153 }
Feb 28 19:53:15 DEBUG GRPC stderr id="nemo-parakeet-tdt-0.6b-127.0.0.1:44879" line=" manifest_filepath: null" caller={caller.file="/build/pkg/model/process.go" caller.L=153 }
Feb 28 19:53:15 DEBUG GRPC stderr id="nemo-parakeet-tdt-0.6b-127.0.0.1:44879" line=" sample_rate: 16000" caller={caller.file="/build/pkg/model/process.go" caller.L=153 }
Feb 28 19:53:15 DEBUG GRPC stderr id="nemo-parakeet-tdt-0.6b-127.0.0.1:44879" line=" batch_size: 16" caller={caller.file="/build/pkg/model/process.go" caller.L=153 }
Feb 28 19:53:15 DEBUG GRPC stderr id="nemo-parakeet-tdt-0.6b-127.0.0.1:44879" line=" shuffle: false" caller={caller.file="/build/pkg/model/process.go" caller.L=153 }
Feb 28 19:53:15 DEBUG GRPC stderr id="nemo-parakeet-tdt-0.6b-127.0.0.1:44879" line=" max_duration: 40.0" caller={caller.file="/build/pkg/model/process.go" caller.L=153 }
Feb 28 19:53:15 DEBUG GRPC stderr id="nemo-parakeet-tdt-0.6b-127.0.0.1:44879" line=" min_duration: 0.1" caller={caller.file="/build/pkg/model/process.go" caller.L=153 }
Feb 28 19:53:15 DEBUG GRPC stderr id="nemo-parakeet-tdt-0.6b-127.0.0.1:44879" line=" num_workers: 2" caller={caller.file="/build/pkg/model/process.go" caller.L=153 }
Feb 28 19:53:15 DEBUG GRPC stderr id="nemo-parakeet-tdt-0.6b-127.0.0.1:44879" line=" pin_memory: true" caller={caller.file="/build/pkg/model/process.go" caller.L=153 }
Feb 28 19:53:15 DEBUG GRPC stderr id="nemo-parakeet-tdt-0.6b-127.0.0.1:44879" line=" text_field: answer" caller={caller.file="/build/pkg/model/process.go" caller.L=153 }
Feb 28 19:53:15 DEBUG GRPC stderr id="nemo-parakeet-tdt-0.6b-127.0.0.1:44879" line=" " caller={caller.file="/build/pkg/model/process.go" caller.L=153 }
Feb 28 19:53:15 DEBUG GRPC stdout id="nemo-parakeet-tdt-0.6b-127.0.0.1:44879" line="[NeMo I 2026-02-28 19:53:15 features:306] PADDING: 0" caller={caller.file="/build/pkg/model/process.go" caller.L=162 }
Feb 28 19:53:20 DEBUG GRPC stdout id="nemo-parakeet-tdt-0.6b-127.0.0.1:44879" line="[NeMo I 2026-02-28 19:53:20 rnnt_models:226] Using RNNT Loss : tdt" caller={caller.file="/build/pkg/model/process.go" caller.L=162 }
Feb 28 19:53:20 DEBUG GRPC stdout id="nemo-parakeet-tdt-0.6b-127.0.0.1:44879" line=" Loss tdt_kwargs: {'fastemit_lambda': 0.0, 'clamp': -1.0, 'durations': [0, 1, 2, 3, 4], 'sigma': 0.02, 'omega': 0.1}" caller={caller.file="/build/pkg/model/process.go" caller.L=162 }
Feb 28 19:53:20 DEBUG GRPC stdout id="nemo-parakeet-tdt-0.6b-127.0.0.1:44879" line="[NeMo I 2026-02-28 19:53:20 rnnt_models:226] Using RNNT Loss : tdt" caller={caller.file="/build/pkg/model/process.go" caller.L=162 }
Feb 28 19:53:20 DEBUG GRPC stdout id="nemo-parakeet-tdt-0.6b-127.0.0.1:44879" line=" Loss tdt_kwargs: {'fastemit_lambda': 0.0, 'clamp': -1.0, 'durations': [0, 1, 2, 3, 4], 'sigma': 0.02, 'omega': 0.1}" caller={caller.file="/build/pkg/model/process.go" caller.L=162 }
Feb 28 19:53:20 DEBUG GRPC stderr id="nemo-parakeet-tdt-0.6b-127.0.0.1:44879" line="[NeMo W 2026-02-28 19:53:20 label_looping_base:109] No conditional node support for Cuda." caller={caller.file="/build/pkg/model/process.go" caller.L=153 }
Feb 28 19:53:20 DEBUG GRPC stderr id="nemo-parakeet-tdt-0.6b-127.0.0.1:44879" line=" Cuda graphs with while loops are disabled, decoding speed will be slower" caller={caller.file="/build/pkg/model/process.go" caller.L=153 }
Feb 28 19:53:20 DEBUG GRPC stderr id="nemo-parakeet-tdt-0.6b-127.0.0.1:44879" line=" Reason: CUDA is not available" caller={caller.file="/build/pkg/model/process.go" caller.L=153 }
Feb 28 19:53:20 DEBUG GRPC stdout id="nemo-parakeet-tdt-0.6b-127.0.0.1:44879" line="[NeMo I 2026-02-28 19:53:20 rnnt_models:226] Using RNNT Loss : tdt" caller={caller.file="/build/pkg/model/process.go" caller.L=162 }
Feb 28 19:53:20 DEBUG GRPC stdout id="nemo-parakeet-tdt-0.6b-127.0.0.1:44879" line=" Loss tdt_kwargs: {'fastemit_lambda': 0.0, 'clamp': -1.0, 'durations': [0, 1, 2, 3, 4], 'sigma': 0.02, 'omega': 0.1}" caller={caller.file="/build/pkg/model/process.go" caller.L=162 }
Feb 28 19:53:20 DEBUG GRPC stderr id="nemo-parakeet-tdt-0.6b-127.0.0.1:44879" line="[NeMo W 2026-02-28 19:53:20 label_looping_base:109] No conditional node support for Cuda." caller={caller.file="/build/pkg/model/process.go" caller.L=153 }
Feb 28 19:53:20 DEBUG GRPC stderr id="nemo-parakeet-tdt-0.6b-127.0.0.1:44879" line=" Cuda graphs with while loops are disabled, decoding speed will be slower" caller={caller.file="/build/pkg/model/process.go" caller.L=153 }
Feb 28 19:53:20 DEBUG GRPC stderr id="nemo-parakeet-tdt-0.6b-127.0.0.1:44879" line=" Reason: CUDA is not available" caller={caller.file="/build/pkg/model/process.go" caller.L=153 }
Feb 28 19:53:22 DEBUG GRPC stderr id="nemo-parakeet-tdt-0.6b-127.0.0.1:44879" line="NEMO ASR model loaded successfully" caller={caller.file="/build/pkg/model/process.go" caller.L=153 }
Feb 28 19:53:22 DEBUG GRPC stdout id="nemo-parakeet-tdt-0.6b-127.0.0.1:44879" line="[NeMo I 2026-02-28 19:53:22 save_restore_connector:284] Model EncDecRNNTBPEModel was successfully restored from /models/models--nvidia--parakeet-tdt-0.6b-v3/snapshots/6d590f77001d318fb17a0b5bf7ee329a91b52598/parakeet-tdt-0.6b-v3.nemo." caller={caller.file="/build/pkg/model/process.go" caller.L=162 }
Feb 28 19:53:22 DEBUG reading file for dynamic config update filename="/configuration/api_keys.json" caller={caller.file="/build/core/application/config_file_watcher.go" caller.L=65 }
Feb 28 19:53:22 DEBUG processing api keys runtime update numKeys=0 caller={caller.file="/build/core/application/config_file_watcher.go" caller.L=138 }
Feb 28 19:53:22 DEBUG no API keys discovered from dynamic config file caller={caller.file="/build/core/application/config_file_watcher.go" caller.L=152 }
Feb 28 19:53:22 DEBUG total api keys after processing numKeys=0 caller={caller.file="/build/core/application/config_file_watcher.go" caller.L=155 }
Feb 28 19:53:22 DEBUG reading file for dynamic config update filename="/configuration/external_backends.json" caller={caller.file="/build/core/application/config_file_watcher.go" caller.L=65 }
Feb 28 19:53:22 DEBUG processing external_backends.json caller={caller.file="/build/core/application/config_file_watcher.go" caller.L=164 }
Feb 28 19:53:22 DEBUG external backends loaded from external_backends.json caller={caller.file="/build/core/application/config_file_watcher.go" caller.L=181 }
Feb 28 19:53:22 DEBUG reading file for dynamic config update filename="/configuration/runtime_settings.json" caller={caller.file="/build/core/application/config_file_watcher.go" caller.L=65 }
Feb 28 19:53:22 DEBUG processing runtime_settings.json caller={caller.file="/build/core/application/config_file_watcher.go" caller.L=189 }
Feb 28 19:53:22 DEBUG runtime settings loaded from runtime_settings.json caller={caller.file="/build/core/application/config_file_watcher.go" caller.L=359 }
Feb 28 19:53:22 INFO core/startup process completed! caller={caller.file="/build/core/application/startup.go" caller.L=163 }
Feb 28 19:53:22 INFO LocalAI is started and running address=":8080" caller={caller.file="/build/core/cli/run.go" caller.L=293 }
Feb 28 19:53:26 INFO HTTP request method="GET" path="/readyz" status=200 caller={caller.file="/build/core/http/app.go" caller.L=118 }
Feb 28 19:53:56 INFO HTTP request method="GET" path="/readyz" status=200 caller={caller.file="/build/core/http/app.go" caller.L=118 }
Feb 28 19:54:26 INFO HTTP request method="GET" path="/readyz" status=200 caller={caller.file="/build/core/http/app.go" caller.L=118 }
Feb 28 19:54:37 DEBUG overriding empty model name in request body with value found earlier in middleware chain context localModelName="nemo-parakeet-tdt-0.6b" caller={caller.file="/build/core/http/middleware/request.go" caller.L=138 }
Feb 28 19:54:37 DEBUG input.Input input="<nil>" caller={caller.file="/build/core/http/middleware/request.go" caller.L=412 }
Feb 28 19:54:37 DEBUG Audio file copied dst="/tmp/whisper2224795340/samples_jfk.wav" caller={caller.file="/build/core/http/endpoints/openai/transcription.go" caller.L=74 }
Feb 28 19:54:37 DEBUG Model already loaded in memory model="nemo-parakeet-tdt-0.6b" caller={caller.file="/build/pkg/model/loader.go" caller.L=256 }
Feb 28 19:54:37 DEBUG Checking model availability model="nemo-parakeet-tdt-0.6b" caller={caller.file="/build/pkg/model/loader.go" caller.L=259 }
Feb 28 19:54:37 DEBUG Model already loaded model="nemo-parakeet-tdt-0.6b" caller={caller.file="/build/pkg/model/initializers.go" caller.L=246 }
Feb 28 19:54:37 DEBUG GRPC stderr id="nemo-parakeet-tdt-0.6b-127.0.0.1:44879" line="[NeMo W 2026-02-28 19:54:37 dataloader:743] The following configuration keys are ignored by Lhotse dataloader: use_start_end_token" caller={caller.file="/build/pkg/model/process.go" caller.L=153 }
Feb 28 19:54:37 DEBUG GRPC stderr id="nemo-parakeet-tdt-0.6b-127.0.0.1:44879" line="[NeMo W 2026-02-28 19:54:37 dataloader:488] You are using a non-tarred dataset and requested tokenization during data sampling (pretokenize=True). This will cause the tokenization to happen in the main (GPU) process,possibly impacting the training speed if your tokenizer is very large.If the impact is noticable, set pretokenize=False in dataloader config.(note: that will disable token-per-second filtering and 2D bucketing features)" caller={caller.file="/build/pkg/model/process.go" caller.L=153 }
Feb 28 19:54:37 DEBUG GRPC stderr id="nemo-parakeet-tdt-0.6b-127.0.0.1:44879" line="Error in AudioTranscription: object.__init__() takes exactly one argument (the instance to initialize)" caller={caller.file="/build/pkg/model/process.go" caller.L=153 }
Feb 28 19:54:37 DEBUG GRPC stderr id="nemo-parakeet-tdt-0.6b-127.0.0.1:44879" line="Traceback (most recent call last):" caller={caller.file="/build/pkg/model/process.go" caller.L=153 }
Feb 28 19:54:37 DEBUG GRPC stderr id="nemo-parakeet-tdt-0.6b-127.0.0.1:44879" line=" File \"/backends/intel-nemo/backend.py\", line 93, in AudioTranscription" caller={caller.file="/build/pkg/model/process.go" caller.L=153 }
Feb 28 19:54:37 DEBUG GRPC stderr id="nemo-parakeet-tdt-0.6b-127.0.0.1:44879" line=" results = self.model.transcribe([audio_path])" caller={caller.file="/build/pkg/model/process.go" caller.L=153 }
Feb 28 19:54:37 DEBUG GRPC stderr id="nemo-parakeet-tdt-0.6b-127.0.0.1:44879" line=" File \"/backends/intel-nemo/venv/lib/python3.10/site-packages/torch/utils/_contextlib.py\", line 124, in decorate_context" caller={caller.file="/build/pkg/model/process.go" caller.L=153 }
Feb 28 19:54:37 DEBUG GRPC stderr id="nemo-parakeet-tdt-0.6b-127.0.0.1:44879" line=" return func(*args, **kwargs)" caller={caller.file="/build/pkg/model/process.go" caller.L=153 }
Feb 28 19:54:37 DEBUG GRPC stderr id="nemo-parakeet-tdt-0.6b-127.0.0.1:44879" line=" File \"/backends/intel-nemo/venv/lib/python3.10/site-packages/nemo/collections/asr/models/rnnt_models.py\", line 306, in transcribe" caller={caller.file="/build/pkg/model/process.go" caller.L=153 }
Feb 28 19:54:37 DEBUG GRPC stderr id="nemo-parakeet-tdt-0.6b-127.0.0.1:44879" line=" return super().transcribe(" caller={caller.file="/build/pkg/model/process.go" caller.L=153 }
Feb 28 19:54:37 DEBUG GRPC stderr id="nemo-parakeet-tdt-0.6b-127.0.0.1:44879" line=" File \"/backends/intel-nemo/venv/lib/python3.10/site-packages/torch/utils/_contextlib.py\", line 124, in decorate_context" caller={caller.file="/build/pkg/model/process.go" caller.L=153 }
Feb 28 19:54:37 DEBUG GRPC stderr id="nemo-parakeet-tdt-0.6b-127.0.0.1:44879" line=" return func(*args, **kwargs)" caller={caller.file="/build/pkg/model/process.go" caller.L=153 }
Feb 28 19:54:37 DEBUG GRPC stderr id="nemo-parakeet-tdt-0.6b-127.0.0.1:44879" line=" File \"/backends/intel-nemo/venv/lib/python3.10/site-packages/nemo/collections/asr/parts/mixins/transcription.py\", line 270, in transcribe" caller={caller.file="/build/pkg/model/process.go" caller.L=153 }
Feb 28 19:54:37 DEBUG GRPC stderr id="nemo-parakeet-tdt-0.6b-127.0.0.1:44879" line=" for processed_outputs in generator:" caller={caller.file="/build/pkg/model/process.go" caller.L=153 }
Feb 28 19:54:37 DEBUG GRPC stderr id="nemo-parakeet-tdt-0.6b-127.0.0.1:44879" line=" File \"/backends/intel-nemo/venv/lib/python3.10/site-packages/nemo/collections/asr/parts/mixins/transcription.py\", line 356, in transcribe_generator" caller={caller.file="/build/pkg/model/process.go" caller.L=153 }
Feb 28 19:54:37 DEBUG GRPC stderr id="nemo-parakeet-tdt-0.6b-127.0.0.1:44879" line=" dataloader = self._transcribe_input_processing(audio, transcribe_cfg)" caller={caller.file="/build/pkg/model/process.go" caller.L=153 }
Feb 28 19:54:37 DEBUG GRPC stderr id="nemo-parakeet-tdt-0.6b-127.0.0.1:44879" line=" File \"/backends/intel-nemo/venv/lib/python3.10/site-packages/nemo/collections/asr/parts/mixins/transcription.py\", line 473, in _transcribe_input_processing" caller={caller.file="/build/pkg/model/process.go" caller.L=153 }
Feb 28 19:54:37 DEBUG GRPC stderr id="nemo-parakeet-tdt-0.6b-127.0.0.1:44879" line=" temp_dataloader = self._setup_transcribe_dataloader(ds_config)" caller={caller.file="/build/pkg/model/process.go" caller.L=153 }
Feb 28 19:54:37 DEBUG GRPC stderr id="nemo-parakeet-tdt-0.6b-127.0.0.1:44879" line=" File \"/backends/intel-nemo/venv/lib/python3.10/site-packages/nemo/collections/asr/models/rnnt_bpe_models.py\", line 616, in _setup_transcribe_dataloader" caller={caller.file="/build/pkg/model/process.go" caller.L=153 }
Feb 28 19:54:37 DEBUG GRPC stderr id="nemo-parakeet-tdt-0.6b-127.0.0.1:44879" line=" temporary_datalayer = self._setup_dataloader_from_config(config=DictConfig(dl_config))" caller={caller.file="/build/pkg/model/process.go" caller.L=153 }
Feb 28 19:54:37 DEBUG GRPC stderr id="nemo-parakeet-tdt-0.6b-127.0.0.1:44879" line=" File \"/backends/intel-nemo/venv/lib/python3.10/site-packages/nemo/collections/asr/models/rnnt_bpe_models.py\", line 510, in _setup_dataloader_from_config" caller={caller.file="/build/pkg/model/process.go" caller.L=153 }
Feb 28 19:54:37 DEBUG GRPC stderr id="nemo-parakeet-tdt-0.6b-127.0.0.1:44879" line=" return get_lhotse_dataloader_from_config(" caller={caller.file="/build/pkg/model/process.go" caller.L=153 }
Feb 28 19:54:37 DEBUG GRPC stderr id="nemo-parakeet-tdt-0.6b-127.0.0.1:44879" line=" File \"/backends/intel-nemo/venv/lib/python3.10/site-packages/nemo/collections/common/data/lhotse/dataloader.py\", line 266, in get_lhotse_dataloader_from_config" caller={caller.file="/build/pkg/model/process.go" caller.L=153 }
Feb 28 19:54:37 DEBUG GRPC stderr id="nemo-parakeet-tdt-0.6b-127.0.0.1:44879" line=" return get_lhotse_dataloader_from_single_config(" caller={caller.file="/build/pkg/model/process.go" caller.L=153 }
Feb 28 19:54:37 DEBUG GRPC stderr id="nemo-parakeet-tdt-0.6b-127.0.0.1:44879" line=" File \"/backends/intel-nemo/venv/lib/python3.10/site-packages/nemo/collections/common/data/lhotse/dataloader.py\", line 306, in get_lhotse_dataloader_from_single_config" caller={caller.file="/build/pkg/model/process.go" caller.L=153 }
Feb 28 19:54:37 DEBUG GRPC stderr id="nemo-parakeet-tdt-0.6b-127.0.0.1:44879" line=" sampler, use_iterable_dataset = get_lhotse_sampler_from_config(" caller={caller.file="/build/pkg/model/process.go" caller.L=153 }
Feb 28 19:54:37 DEBUG GRPC stderr id="nemo-parakeet-tdt-0.6b-127.0.0.1:44879" line=" File \"/backends/intel-nemo/venv/lib/python3.10/site-packages/nemo/collections/common/data/lhotse/dataloader.py\", line 595, in get_lhotse_sampler_from_config" caller={caller.file="/build/pkg/model/process.go" caller.L=153 }
Feb 28 19:54:37 DEBUG GRPC stderr id="nemo-parakeet-tdt-0.6b-127.0.0.1:44879" line=" sampler = DynamicCutSampler(" caller={caller.file="/build/pkg/model/process.go" caller.L=153 }
Feb 28 19:54:37 DEBUG GRPC stderr id="nemo-parakeet-tdt-0.6b-127.0.0.1:44879" line=" File \"/backends/intel-nemo/venv/lib/python3.10/site-packages/lhotse/dataset/sampling/dynamic.py\", line 120, in __init__" caller={caller.file="/build/pkg/model/process.go" caller.L=153 }
Feb 28 19:54:37 DEBUG GRPC stderr id="nemo-parakeet-tdt-0.6b-127.0.0.1:44879" line=" super().__init__(" caller={caller.file="/build/pkg/model/process.go" caller.L=153 }
Feb 28 19:54:37 DEBUG GRPC stderr id="nemo-parakeet-tdt-0.6b-127.0.0.1:44879" line=" File \"/backends/intel-nemo/venv/lib/python3.10/site-packages/lhotse/dataset/sampling/base.py\", line 77, in __init__" caller={caller.file="/build/pkg/model/process.go" caller.L=153 }
Feb 28 19:54:37 DEBUG GRPC stderr id="nemo-parakeet-tdt-0.6b-127.0.0.1:44879" line=" super().__init__(" caller={caller.file="/build/pkg/model/process.go" caller.L=153 }
Feb 28 19:54:37 DEBUG GRPC stderr id="nemo-parakeet-tdt-0.6b-127.0.0.1:44879" line="TypeError: object.__init__() takes exactly one argument (the instance to initialize)" caller={caller.file="/build/pkg/model/process.go" caller.L=153 }
Feb 28 19:54:37 DEBUG Transcribed transcription=&{[] } caller={caller.file="/build/core/http/endpoints/openai/transcription.go" caller.L=81 }
Feb 28 19:54:37 INFO HTTP request method="POST" path="/v1/audio/transcriptions" status=200 caller={caller.file="/build/core/http/app.go" caller.L=118 }
Additional context
I've tried both intel-nemo and cpu-nemo backends and neither work.