Parakeet TDT#
The Parakeet TDT NIM supports only the offline API.
For client installation and sample audio instructions, refer to the Deploy and Run ASR Models page.
Deploy the NIM Container#
export CONTAINER_ID=parakeet-tdt-0.6b-v2
export NIM_TAGS_SELECTOR="name=parakeet-tdt-0.6b-v2,mode=ofl"
docker run -it --rm --name=$CONTAINER_ID \
--runtime=nvidia \
--gpus '"device=0"' \
--shm-size=8GB \
-e NGC_API_KEY \
-e NIM_HTTP_API_PORT=9000 \
-e NIM_GRPC_API_PORT=50051 \
-p 9000:9000 \
-p 50051:50051 \
-e NIM_TAGS_SELECTOR \
nvcr.io/nim/nvidia/$CONTAINER_ID:latest
For additional profile options, refer to the ASR support matrix.
Run Inference#
Copy a sample audio file from the NIM container or use your own.
docker cp $CONTAINER_ID:/opt/riva/wav/en-US_sample.wav .
Ensure the NIM is deployed with an offline mode model.
python3 python-clients/scripts/asr/transcribe_file_offline.py \
--server 0.0.0.0:50051 \
--list-models
python3 python-clients/scripts/asr/transcribe_file_offline.py \
--server 0.0.0.0:50051 \
--language-code en-US \
--input-file en-US_sample.wav
curl -s http://0.0.0.0:9000/v1/audio/transcriptions -F language=en-US \
-F file="@en-US_sample.wav"
Parakeet TDT Multilingual supports offline transcription in multiple languages. The model identifies the spoken language and returns the transcript. Use language code multi for auto language detection.
Copy sample audio files from the NIM container to the host machine, or use your own.
Note
Language code multi is mandatory for auto language detection.
docker cp $CONTAINER_ID:/opt/riva/wav/fr-FR_sample.wav .
Ensure the NIM is deployed with an offline mode model.
python3 python-clients/scripts/asr/transcribe_file_offline.py \
--server 0.0.0.0:50051 \
--list-models
python3 python-clients/scripts/asr/transcribe_file_offline.py \
--server 0.0.0.0:50051 \
--language-code multi \
--input-file fr-FR_sample.wav
curl -s http://0.0.0.0:9000/v1/audio/transcriptions -F language=multi \
-F file="@fr-FR_sample.wav"