nvidia
nvidia/parakeet-tdt-0.6b-v3
trackdownloads: true - en - es - fr - de - bg - hr - cs - da - nl - et - fi - el - hu - it - lv - lt - mt - pl - pt - ro - sk - sl - sv - ru...
Model Documentation
🦜 parakeet-tdt-0.6b-v3: Multilingual Speech-to-Text Model
| 
| 
Description:
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.🗣️ Try Demo here: https://huggingface.co/spaces/nvidia/parakeet-tdt-0.6b-v3
Supported Languages: Bulgarian (bg), Croatian (hr), Czech (cs), Danish (da), Dutch (nl), English (en), Estonian (et), Finnish (fi), French (fr), German (de), Greek (el), Hungarian (hu), Italian (it), Latvian (lv), Lithuanian (lt), Maltese (mt), Polish (pl), Portuguese (pt), Romanian (ro), Slovak (sk), Slovenian (sl), Spanish (es), Swedish (sv), Russian (ru), Ukrainian (uk)
This model is ready for commercial/non-commercial use.
Key Features:
parakeet-tdt-0.6b-v3's key features are built on the foundation of its predecessor, parakeet-tdt-0.6b-v2, and include:* Automatic punctuation and capitalization * Accurate word-level and segment-level timestamps * Long audio transcription, supporting audio up to 24 minutes long with full attention (on A100 80GB) or up to 3 hours with local attention. * Released under a permissive CC BY 4.0 license
For full details on the model architecture, training methodology, datasets, and evaluation results, check out the Technical Report.
License/Terms of Use:
GOVERNING TERMS: Use of this model is governed by the CC-BY-4.0 license.
Discover more from NVIDIA:
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.#
Explore more from NVIDIA:
What is Nemotron?NVIDIA Developer Nemotron
NVIDIA Riva Speech
NeMo Documentation
Automatic Speech Recognition (ASR) Performance
*Figure 1: ASR WER comparison across different models. This does not include Punctuation and Capitalisation errors.*
---
Evaluation Notes
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
Deployment Geography:
GlobalUse Case:
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.
Release Date:
Huggingface 08/14/2025
Model Architecture:
Architecture Type:
FastConformer-TDT
Network Architecture:
* This model was developed based on FastConformer encoder architecture[3] and TDT decoder[4] * This model has 600 million model parameters.
Input:
Input Type(s): 16kHz Audio Input Format(s):.wav and .flac audio formats
Input Parameters: 1D (audio signal)
Other Properties Related to Input: Monochannel audioOutput:
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.
For more information, refer to the NeMo documentation.
How to Use this Model:
To train, fine-tune or play with the model you will need to install NVIDIA NeMo. We recommend you install it after you've installed latest PyTorch version.
bash
pip install -U nemo_toolkit['asr']
#
Automatically instantiate the model
python
import nemo.collections.asr as nemo_asr
asr_model = nemo_asr.models.ASRModel.from_pretrained(model_name="nvidia/parakeet-tdt-0.6b-v3")
#
Transcribing using Python
First, let's get a samplebash
wget https://dldata-public.s3.us-east-2.amazonaws.com/2086-149220-0033.wav
python
output = asr_model.transcribe(['2086-149220-0033.wav'])
print(output[0].text)
#
Transcribing with timestamps
To transcribe with timestamps:
python
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']}")
#
Transcribing long-form audio
python
#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)
#
Streaming with Parakeet models
To use parakeet models in streaming mode use this script as shown below:
bash
python NeMo/main/examples/asr/asr_chunked_inference/rnnt/speech_to_text_streaming_infer_rnnt.py \
pretrained_name="nvidia/parakeet-tdt-0.6b-v3" \
model_path=null \
audio_dir="" \
dataset_manifest="" \
output_filename="" \
right_context_secs=2.0 \
chunk_secs=2 \
left_context_secs=10.0 \
batch_size=32 \
clean_groundtruth_text=False
NVIDIA NIM for v2 parakeet model is available at https://build.nvidia.com/nvidia/parakeet-tdt-0_6b-v2.
Software Integration:
Runtime Engine(s): * NeMo 2.4
Supported Hardware Microarchitecture Compatibility: * NVIDIA Ampere * NVIDIA Blackwell * NVIDIA Hopper * NVIDIA Volta
[Preferred/Supported] Operating System(s):
Hardware Specific Requirements:
Atleast 2GB RAM for model to load. The bigger the RAM, the larger audio input it supports.
#
Model Version
Current version:
parakeet-tdt-0.6b-v3. Previous versions can be accessed here. Training and Evaluation Datasets:
Training
This model was trained using the NeMo toolkit [5], following the strategies below:
Training was conducted using this example script and TDT configuration.
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.
Training Dataset
The model was trained on the combination of Granary dataset's ASR subset and in-house dataset NeMo ASR Set 3.0:All transcriptions preserve punctuation and capitalization. The Granary dataset will be made publicly available after presentation at Interspeech 2025.
Data Collection Method by dataset
* Hybrid: Automated, Human
Labeling Method by dataset
* Hybrid: Synthetic, Human
Properties:
* Noise robust data from various sources * Single channel, 16kHz sampled data
#
Evaluation Datasets
For multilingual ASR performance evaluation:
For English ASR performance evaluation:
Data Collection Method by dataset * Human
Labeling Method by dataset * Human
Properties:
* All are commonly used for benchmarking English ASR systems. * Audio data is typically processed into a 16kHz mono channel format for ASR evaluation, consistent with benchmarks like the Open ASR Leaderboard.
Performance
#
Multilingual ASR
The tables below summarizes the WER (%) using a Transducer decoder with greedy decoding (without an external language model):
| Language | Fleurs | MLS | CoVoST | |----------|--------|-----|--------| | Average WER ↓ | *11.97%* | *7.83%* | *11.98%* | | bg | 12.64% |
Note: WERs are calculated after removing Punctuation and Capitalization from reference and predicted text.
#
Huggingface Open-ASR-Leaderboard
| Model | Avg WER | AMI | Earnings-22 | GigaSpeech | LS test-clean | LS test-other | SPGI Speech | TEDLIUM-v3 | VoxPopuli | |:-------------|:-------------:|:---------:|:------------------:|:----------------:|:-----------------:|:-----------------:|:------------------:|:----------------:|:---------------:| |
parakeet-tdt-0.6b-v3 | 6.34% | 11.31% | 11.42% | 9.59% | 1.93% | 3.59% | 3.97% | 2.75% | 6.14% |Additional evaluation details are available on the Hugging Face ASR Leaderboard.[13]
Noise Robustness
Performance across different Signal-to-Noise Ratios (SNR) using MUSAN music and noise samples [14]:| SNR Level | Avg WER | AMI | Earnings | GigaSpeech | LS test-clean | LS test-other | SPGI | Tedlium | VoxPopuli | Relative Change | |:---------------|:-------------:|:----------:|:------------:|:----------------:|:-----------------:|:-----------------:|:-----------:|:-------------:|:---------------:|:-----------------:| | Clean | 6.34% | 11.31% | 11.42% | 9.59% | 1.93% | 3.59% | 3.97% | 2.75% | 6.14% |
References
1] [Granary: Speech Recognition and Translation Dataset in 25 European Languages
2] [NVIDIA Granary Dataset Card
3] [Fast Conformer with Linearly Scalable Attention for Efficient Speech Recognition
4] [Efficient Sequence Transduction by Jointly Predicting Tokens and Durations
5] [NVIDIA NeMo Toolkit
6] [Google Sentencepiece Tokenizer
7] [Youtube-Commons
8] [MOSEL: 950,000 Hours of Speech Data for Open-Source Speech Foundation Model Training on EU Languages
9] [YODAS: Youtube-Oriented Dataset for Audio and Speech
10] [FLEURS: Few-shot Learning Evaluation of Universal Representations of Speech
11] [MLS: A Large-Scale Multilingual Dataset for Speech Research
12] [CoVoST 2 and Massively Multilingual Speech-to-Text Translation
13] [HuggingFace ASR Leaderboard
14] [MUSAN: A Music, Speech, and Noise Corpus
Inference:
Engine: * NVIDIA NeMo
Test Hardware: * NVIDIA A10 * NVIDIA A100 * NVIDIA A30 * NVIDIA H100 * NVIDIA L4 * NVIDIA L40 * NVIDIA Turing T4 * NVIDIA Volta V100
Ethical Considerations:
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.
Bias:
Field | Response ---------------------------------------------------------------------------------------------------|--------------- Participation considerations from adversely impacted groups protected classes in model design and testing | None Measures taken to mitigate against unwanted bias | None
Explainability:
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.
Privacy:
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/
Safety:
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 & Weights
| Filename | Size | Action |
|---|