Parakeet TDT 0.6B V3
Parakeet TDT 0.6B V3Parakeet-tdt-0.6b-v3 is a 600-million-parameter multilingual automatic speech recognition (ASR) model designed for high-throughput speech-to-text transcription.
Model details
View repositoryParakeet-tdt-0.6b-v3 is a 600-million-parameter multilingual automatic speech recognition (ASR) model designed for high-throughput speech-to-text transcription. It extends the parakeet-tdt-0.6b-v2 model by expanding language support from English to 25 European languages. The model automatically detects the language of the audio and transcribes it without requiring additional prompting. It is part of a series of models that leverage the Granary multilingual corpus as their primary training dataset.
Batch performance
The charts below show median latency and unit economics (cost per audio hour) change with audio length when transcribing prerecorded files at 1, 4 and 16 concurrent requests per GPU. Higher concurrency significantly reduces cost per audio hour, with a corresponding tradeoff in latency that grows with audio length.
Concurrency is configurable and can be tuned to achieve the latency and cost targets that best fit your workload and business requirements. See the concurrency guide for configuration details.
For batch workloads, we recommend starting with RTX6000 using concurrency 16, and lowering it to reduce latency on longer audio or raising it to increase throughput on latency tolerant workloads
Using the model
1import os
2import requests
3
4model_id = "<MODEL_ID>"
5
6response = requests.post(
7 f"https://model-{model_id}.api.baseten.co/environments/production/predict",
8 headers={"Authorization": f"Api-Key {os.environ['BASETEN_API_KEY']}"},
9 json={"audio_url": "https://example.com/audio.wav"},
10)
11response.raise_for_status()
12
13print(response.json())1{
2 "transcript": "Well, I don't wish to see it any more, observed Phoebe, turning away her eyes. It is certainly very like the old portrait.",
3 "text": "Well, I don't wish to see it any more, observed Phoebe, turning away her eyes. It is certainly very like the old portrait."
4}Contact us
For workload-specific optimization, you can contact an engineer for further assistance.
