parakeet-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 [1, 2] multilingual corpus as their primary training dataset.
For documentation, deployment guides, enterprise-ready APIs, and the latest open models—including Nemotron and other cutting-edge speech, translation, and generative AI—visit the NVIDIA Developer Portal at developer.nvidia.com. Join the community to access tools, support, and resources to accelerate your development with NVIDIA’s NeMo, Riva, NIM, and foundation models.
Note 1: The above evaluations are conducted for 24 supported languages, excluding Latvian since seamless-m4t-v2-large and seamless-m4t-medium do not support it.
Note 2: Performance differences may be partly attributed to Portuguese variant differences - our training data uses European Portuguese while most benchmarks use Brazilian Portuguese.
This model serves developers, researchers, academics, and industries building applications that require speech-to-text capabilities, including but not limited to: conversational AI, voice assistants, transcription services, subtitle generation, and voice analytics platforms.
Output Type(s): Text Output Format: String Output Parameters: 1D (text) Other Properties Related to Output: Punctuations and Capitalizations included.
Our AI models are designed and/or optimized to run on NVIDIA GPU-accelerated systems. By leveraging NVIDIA's hardware (e.g. GPU cores) and software frameworks (e.g., CUDA libraries), the model achieves faster training and inference times compared to CPU-only solutions.
To train, fine-tune, or run Python inference with this model, install NVIDIA NeMo after installing a recent PyTorch version.
pip install -U nemo_toolkit['asr']
The model is available for use in the NeMo toolkit [5], and can be used as a pre-trained checkpoint for inference or for fine-tuning on another dataset.
You can also run Parakeet TDT with Transformers 🤗 (more below).
output = asr_model.transcribe(['2086-149220-0033.wav'], timestamps=True)
# by default, timestamps are enabled for char, word and segment level
word_timestamps = output[0].timestamp['word'] # word level timestamps for first sample
segment_timestamps = output[0].timestamp['segment'] # segment level timestamps
char_timestamps = output[0].timestamp['char'] # char level timestamps
for stamp in segment_timestamps:
print(f"{stamp['start']}s - {stamp['end']}s : {stamp['segment']}")
#updating self-attention model of fast-conformer encoder
#setting attention left and right context sizes to 256
asr_model.change_attention_model(self_attention_model="rel_pos_local_attn", att_context_size=[256, 256])
output = asr_model.transcribe(['2086-149220-0033.wav'])
print(output[0].text)
This model was trained using the NeMo toolkit [5], following the strategies below:
Initialized from a CTC multilingual checkpoint pretrained on the Granary dataset \[1] \[2].
Trained for 150,000 steps on 128 A100 GPUs.
Dataset corpora and languages were balanced using a temperature sampling value of 0.5.
Stage 2 fine-tuning was performed for 5,000 steps on 4 A100 GPUs using approximately 7,500 hours of high-quality, human-transcribed data of NeMo ASR Set 3.0.
During the training, a unified SentencePiece Tokenizer \[6] with a vocabulary of 8,192 tokens was used. The unified tokenizer was constructed from the training set transcripts using this script and was optimized across all 25 supported languages.
All transcriptions preserve punctuation and capitalization. The Granary dataset will be made publicly available after presentation at Interspeech 2025.
NVIDIA believes Trustworthy AI is a shared responsibility and we have established policies and practices to enable development for a wide array of AI applications. When downloaded or used in accordance with our terms of service, developers should work with their supporting model team to ensure this model meets requirements for the relevant industry and use case and addresses unforeseen product misuse.
For more detailed information on ethical considerations for this model, please see the Model Card++ Explainability, Bias, Safety & Security, and Privacy Subcards here.
Please report security vulnerabilities or NVIDIA AI Concerns here.
Field | Response ---------------------------------------------------------------------------------------------------|--------------- Participation considerations from adversely impacted groups protected classes in model design and testing | None Measures taken to mitigate against unwanted bias | None
Field | Response ------------------------------------------------------------------------------------------------------|--------------------------------------------------------------------------------- Intended Domain | Speech to Text Transcription Model Type | FastConformer Intended Users | This model is intended for developers, researchers, academics, and industries building conversational based applications. Output | Text Describe how the model works | Speech input is encoded into embeddings and passed into conformer-based model and output a text response. Name the adversely impacted groups this has been tested to deliver comparable outcomes regardless of | Not Applicable Technical Limitations & Mitigation | Transcripts may be not 100% accurate. Accuracy varies based on language and characteristics of input audio (Domain, Use Case, Accent, Noise, Speech Type, Context of speech, etc.) Verified to have met prescribed NVIDIA quality standards | Yes Performance Metrics | Word Error Rate Potential Known Risks | If a word is not trained in the language model and not presented in vocabulary, the word is not likely to be recognized. Not recommended for word-for-word/incomplete sentences as accuracy varies based on the context of input text Licensing | GOVERNING TERMS: Use of this model is governed by the CC-BY-4.0 license.
Field | Response ----------------------------------------------------------------------------------------------------------------------------------|----------------------------------------------- Generatable or reverse engineerable personal data? | None Personal data used to create this model? | None Is there provenance for all datasets used in training? | Yes Does data labeling (annotation, metadata) comply with privacy laws? | Yes Is data compliant with data subject requests for data correction or removal, if such a request was made? | No, not possible with externally-sourced data. Applicable Privacy Policy | https://www.nvidia.com/en-us/about-nvidia/privacy-policy/
Field | Response ---------------------------------------------------|---------------------------------- Model Application(s) | Speech to Text Transcription Describe the life critical impact | None Use Case Restrictions | Abide by CC-BY-4.0 License Model and dataset restrictions | The Principle of least privilege (PoLP) is applied limiting access for dataset generation and model development. Restrictions enforce dataset access during training, and dataset license constraints adhered to.
Files
12 files · 5.73 GBWeights 714 MB (GGUF). Sizes and sha256 from the signed manifest.
transformersSpeech recognition with the transformers pipeline.
import os
os.environ["HF_ENDPOINT"] = "https://freeweights.allternit.com"
from transformers import pipeline
asr = pipeline("automatic-speech-recognition", model="nvidia/parakeet-tdt-0.6b-v3", revision="541d1f99c6b0c3cd0b11a95167540bb8edefd82b")
print(asr("audio.wav")["text"])
llama.cppDownload one GGUF variant (parakeet-tdt-0.6b-v3.q8_0, 714 MB), then serve it.
nvidia <huggingface.co/nvidia>Newsgroups: alt.freeweights.speechSubject: 
onnx-community 
mlx-community