I’m trying to transcribe audio files using tao speech_to_text_citrinet infer with the following pre-trained citrinet model: https://catalog.ngc.nvidia.com/orgs/nvidia/teams/tao/models/speechtotext_en_us_citrinet ngc registry model download-version "nvidia/tao/speechtotext_en_us_citrinet:trainable_…

[image] nicolas20: tried with different .wav files (mono & 16k sample-rate), Could you share the link or several files?

Could you share some results when you run above two files? You mention that it will get random result.

Yes of course. The hello world sample gives the following result: [NeMo I 2022-03-02 22:11:19 infer:71] File: /data/hello_world.wav [NeMo I 2022-03-02 22:11:19 infer:72] Predicted transcript: sc which them seven sc return And the second sample gives something similar to that: case return indiv…

So, on your side, the inference result are not correct at all. Could you try to run inference against some an4 audio files mentioned in jupyter notebook? https://catalog.ngc.nvidia.com/orgs/nvidia/teams/tao/resources/speechtotext_citrinet_notebook/version/v1.3/files/speech-to-text-training.ipynb

I just tried to download an4 but it seems to be down: http://www.speech.cs.cmu.edu/databases/an4/an4_sphere.tar.gz I saw in the training notebook that they preprocess the audio files using tao speech_to_text_citrinet dataset_convert, so I wanted to apply that to my audio files: ! tao speech_to_tex…

[image] nicolas20: $DATA_DIR Please note that $DATA_DIR should be a path inside the docker. The mapping is defined in tao_mounts.json file.

That I understand, and I put my wav files in the $DATA_DIR. However, dataset_convert seems to be looking for a train.tsv file, but I can’t find the specs for the format of this file in the documentation. (I imagine it should contain the paths of the audio files etc…)

[image] nicolas20: However, dataset_convert seems to be looking for a train.tsv file, I can not understand. Could you try to run the official notebook firstly?

What I’m trying to do is converting my audio files using the dataset_convert command. But this yields the following error: FileNotFoundError: [Errno 2] No such file or directory: '/data/train.tsv …Meaning that it expects a train.tsv file in the $DATA_DIR - and I don’t know what should be the conte…

Speech_to_text_citrinet infer yields random transcription results

Accelerated Computing Intelligent Video Analytics TAO Toolkit

Morganh April 14, 2022, 3:49am 15

Refer to Speech_to_text_citrinet infer yields random transcription results - #5 by Morganh

Topic		Replies	Views
Speech_to_text_citrinet infer yields random transcription results TAO Toolkit	14	1520	July 6, 2022
Any Tips for Fine tuning Citrinet model TAO Toolkit	12	1511	April 25, 2022
Tao speech_to_text evaluate+infer show very weak results TAO Toolkit	25	2460	February 10, 2022
Please support the new canary-1b-v2 und parakeet-tdt-0.6b-v3 models via API Models	4	495	October 3, 2025
Tao Citirnet dataset_convert TAO Toolkit	4	557	August 14, 2022
Speech-to-text STT api docker image with arm64 + GPU support DGX Spark / GB10	1	443	December 29, 2025
Help with custom deploy and perform inference using citrinet-mandarin NGC pre-trained model in Riva Riva riva	5	1343	August 27, 2021
Tao speech_to_text infer -- how can I pass file list? TAO Toolkit	4	723	January 19, 2022
Speech_to_text infer: model_weights.ckpt not found Riva	0	732	February 23, 2022
Request for a Playbook - Train/Fine-Tune a TTS model for speech DGX Spark / GB10	4	422	January 18, 2026

Speech_to_text_citrinet infer yields random transcription results

Related topics