--- license: cc-by-4.0 language: - en pipeline_tag: automatic-speech-recognition library_name: nemo datasets: - librispeech_asr - fisher_corpus - mozilla-foundation/common_voice_8_0 - National-Singapore-Corpus-Part-1 - vctk - voxpopuli - europarl - multilingual_librispeech thumbnail: null tags: - automatic-speech-recognition - speech - audio - Transducer - TDT - FastConformer - Conformer - pytorch - NeMo - hf-asr-leaderboard widget: - example_title: Librispeech sample 1 src: https://cdn-media.huggingface.co/speech_samples/sample1.flac - example_title: Librispeech sample 2 src: https://cdn-media.huggingface.co/speech_samples/sample2.flac model-index: - name: parakeet-tdt-0.6b-v2 results: - task: name: Automatic Speech Recognition type: automatic-speech-recognition dataset: name: AMI (Meetings test) type: edinburghcstr/ami config: ihm split: test args: language: en metrics: - name: Test WER type: wer value: 11.16 - task: name: Automatic Speech Recognition type: automatic-speech-recognition dataset: name: Earnings-22 type: revdotcom/earnings22 split: test args: language: en metrics: - name: Test WER type: wer value: 11.15 - task: name: Automatic Speech Recognition type: automatic-speech-recognition dataset: name: GigaSpeech type: speechcolab/gigaspeech split: test args: language: en metrics: - name: Test WER type: wer value: 9.74 - task: name: Automatic Speech Recognition type: automatic-speech-recognition dataset: name: LibriSpeech (clean) type: librispeech_asr config: other split: test args: language: en metrics: - name: Test WER type: wer value: 1.69 - task: name: Automatic Speech Recognition type: automatic-speech-recognition dataset: name: LibriSpeech (other) type: librispeech_asr config: other split: test args: language: en metrics: - name: Test WER type: wer value: 3.19 - task: type: Automatic Speech Recognition name: automatic-speech-recognition dataset: name: SPGI Speech type: kensho/spgispeech config: test split: test args: language: en metrics: - name: Test WER type: wer value: 2.17 - task: type: Automatic Speech Recognition name: automatic-speech-recognition dataset: name: tedlium-v3 type: LIUM/tedlium config: release1 split: test args: language: en metrics: - name: Test WER type: wer value: 3.38 - task: name: Automatic Speech Recognition type: automatic-speech-recognition dataset: name: Vox Populi type: facebook/voxpopuli config: en split: test args: language: en metrics: - name: Test WER type: wer value: 5.95 metrics: - wer --- # **Parakeet TDT 0.6B V2 (En)** [![Model architecture](https://img.shields.io/badge/Model_Arch-FastConformer--TDT-blue#model-badge)](#model-architecture) | [![Model size](https://img.shields.io/badge/Params-0.6B-green#model-badge)](#model-architecture) | [![Language](https://img.shields.io/badge/Language-en-orange#model-badge)](#datasets) ## Description: `parakeet-tdt-0.6b-v2` is a 600-million-parameter automatic speech recognition (ASR) model designed for high-quality English transcription, featuring support for punctuation, capitalization, and accurate timestamp prediction. Try Demo here: https://huggingface.co/spaces/nvidia/parakeet-tdt-0.6b-v2 This XL variant of the FastConformer [1] architecture integrates the TDT [2] decoder and is trained with full attention, enabling efficient transcription of audio segments up to 24 minutes in a single pass. The model achieves an RTFx of 3380 on the HF-Open-ASR leaderboard with a batch size of 128. Note: *RTFx Performance may vary depending on dataset audio duration and batch size.* **Key Features** - Accurate word-level timestamp predictions - Automatic punctuation and capitalization - Robust performance on spoken numbers, and song lyrics transcription For more information, refer to the [Model Architecture](#model-architecture) section and the [NeMo documentation](https://docs.nvidia.com/deeplearning/nemo/user-guide/docs/en/main/asr/models.html#fast-conformer). This model is ready for commercial/non-commercial use. ## License/Terms of Use: GOVERNING TERMS: Use of this model is governed by the [CC-BY-4.0](https://creativecommons.org/licenses/by/4.0/legalcode.en) license. ### Deployment Geography: Global ### Use 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: 05/01/2025 ### Model Architecture: **Architecture Type**: FastConformer-TDT **Network Architecture**: * This model was developed based on [FastConformer encoder](https://docs.nvidia.com/deeplearning/nemo/user-guide/docs/en/main/asr/models.html#fast-conformer) architecture[1] and TDT decoder[2] * 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 audio ### Output: - **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. ## How to Use this Model: To train, fine-tune or play with the model you will need to install [NVIDIA NeMo](https://github.com/NVIDIA/NeMo). We recommend you install it after you've installed latest PyTorch version. ```bash pip install -U nemo_toolkit['asr'] ``` The model is available for use in the NeMo toolkit [3], and can be used as a pre-trained checkpoint for inference or for fine-tuning on another dataset. #### 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-v2") ``` #### Transcribing using Python First, let's get a sample ```bash wget https://dldata-public.s3.us-east-2.amazonaws.com/2086-149220-0033.wav ``` Then simply do: ```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']}") ``` ## Software Integration: **Runtime Engine(s):** * NeMo 2.2 **Supported Hardware Microarchitecture Compatibility:** * NVIDIA Ampere * NVIDIA Blackwell * NVIDIA Hopper * NVIDIA Volta **[Preferred/Supported] Operating System(s):** - Linux **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-v2. Previous versions can be [accessed](https://huggingface.co/collections/nvidia/parakeet-659711f49d1469e51546e021) here. ## Training and Evaluation Datasets: ### Training This model was trained using the NeMo toolkit [3], following the strategies below: - Initialized from a wav2vec SSL checkpoint pretrained on the LibriLight dataset[7]. - Trained for 150,000 steps on 128 A100 GPUs. - Dataset corpora were balanced using a temperature sampling value of 0.5. - Stage 2 fine-tuning was performed for 2,500 steps on 4 A100 GPUs using approximately 500 hours of high-quality, human-transcribed data of NeMo ASR Set 3.0. Training was conducted using this [example script](https://github.com/NVIDIA/NeMo/blob/main/examples/asr/asr_transducer/speech_to_text_rnnt_bpe.py) and [TDT configuration](https://github.com/NVIDIA/NeMo/blob/main/examples/asr/conf/fastconformer/hybrid_transducer_ctc/fastconformer_hybrid_tdt_ctc_bpe.yaml). The tokenizer was constructed from the training set transcripts using this [script](https://github.com/NVIDIA/NeMo/blob/main/scripts/tokenizers/process_asr_text_tokenizer.py). ### Training Dataset The model was trained on the Granary dataset, consisting of approximately 120,000 hours of English speech data: - 10,000 hours from human-transcribed NeMo ASR Set 3.0, including: - LibriSpeech (960 hours) - Fisher Corpus - National Speech Corpus Part 1 - VCTK - VoxPopuli (English) - Europarl-ASR (English) - Multilingual LibriSpeech (MLS English) – 2,000-hour subset - Mozilla Common Voice (v7.0) - AMI - 110,000 hours of pseudo-labeled data from: - YTC (YouTube-Commons) dataset[4] - YODAS dataset [5] - Librilight [7] 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 Dataset Huggingface Open ASR Leaderboard datasets are used to evaluate the performance of this model. **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](https://huggingface.co/spaces/hf-audio/open_asr_leaderboard). ## Performance #### Huggingface Open-ASR-Leaderboard Performance The performance of Automatic Speech Recognition (ASR) models is measured using Word Error Rate (WER). Given that this model is trained on a large and diverse dataset spanning multiple domains, it is generally more robust and accurate across various types of audio. ### Base Performance The table below summarizes the WER (%) using a Transducer decoder with greedy decoding (without an external language model): | **Model** | **Avg WER** | **AMI** | **Earnings-22** | **GigaSpeech** | **LS test-clean** | **LS test-other** | **SPGI Speech** | **TEDLIUM-v3** | **VoxPopuli** | |:-------------|:-------------:|:---------:|:------------------:|:----------------:|:-----------------:|:-----------------:|:------------------:|:----------------:|:---------------:| | parakeet-tdt-0.6b-v2 | 6.05 | 11.16 | 11.15 | 9.74 | 1.69 | 3.19 | 2.17 | 3.38 | 5.95 | - | ### Noise Robustness Performance across different Signal-to-Noise Ratios (SNR) using MUSAN music and noise samples: | **SNR Level** | **Avg WER** | **AMI** | **Earnings** | **GigaSpeech** | **LS test-clean** | **LS test-other** | **SPGI** | **Tedlium** | **VoxPopuli** | **Relative Change** | |:---------------|:-------------:|:----------:|:------------:|:----------------:|:-----------------:|:-----------------:|:-----------:|:-------------:|:---------------:|:-----------------:| | Clean | 6.05 | 11.16 | 11.15 | 9.74 | 1.69 | 3.19 | 2.17 | 3.38 | 5.95 | - | | SNR 50 | 6.04 | 11.11 | 11.12 | 9.74 | 1.70 | 3.18 | 2.18 | 3.34 | 5.98 | +0.25% | | SNR 25 | 6.50 | 12.76 | 11.50 | 9.98 | 1.78 | 3.63 | 2.54 | 3.46 | 6.34 | -7.04% | | SNR 5 | 8.39 | 19.33 | 13.83 | 11.28 | 2.36 | 5.50 | 3.91 | 3.91 | 6.96 | -38.11% | ### Telephony Audio Performance Performance comparison between standard 16kHz audio and telephony-style audio (using μ-law encoding with 16kHz→8kHz→16kHz conversion): | **Audio Format** | **Avg WER** | **AMI** | **Earnings** | **GigaSpeech** | **LS test-clean** | **LS test-other** | **SPGI** | **Tedlium** | **VoxPopuli** | **Relative Change** | |:-----------------|:-------------:|:----------:|:------------:|:----------------:|:-----------------:|:-----------------:|:-----------:|:-------------:|:---------------:|:-----------------:| | Standard 16kHz | 6.05 | 11.16 | 11.15 | 9.74 | 1.69 | 3.19 | 2.17 | 3.38 | 5.95 | - | | μ-law 8kHz | 6.32 | 11.98 | 11.16 | 10.02 | 1.78 | 3.52 | 2.20 | 3.38 | 6.52 | -4.10% | These WER scores were obtained using greedy decoding without an external language model. Additional evaluation details are available on the [Hugging Face ASR Leaderboard](https://huggingface.co/spaces/hf-audio/open_asr_leaderboard).[6] ## References [1] [Fast Conformer with Linearly Scalable Attention for Efficient Speech Recognition](https://arxiv.org/abs/2305.05084) [2] [Efficient Sequence Transduction by Jointly Predicting Tokens and Durations](https://arxiv.org/abs/2304.06795) [3] [NVIDIA NeMo Toolkit](https://github.com/NVIDIA/NeMo) [4] [Youtube-commons: A massive open corpus for conversational and multimodal data](https://huggingface.co/blog/Pclanglais/youtube-commons) [5] [Yodas: Youtube-oriented dataset for audio and speech](https://arxiv.org/abs/2406.00899) [6] [HuggingFace ASR Leaderboard](https://huggingface.co/spaces/hf-audio/open_asr_leaderboard) [7] [MOSEL: 950,000 Hours of Speech Data for Open-Source Speech Foundation Model Training on EU Languages](https://arxiv.org/abs/2410.01036) ## 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](https://developer.nvidia.com/blog/enhancing-ai-transparency-and-ethical-considerations-with-model-card/). Please report security vulnerabilities or NVIDIA AI Concerns [here](https://www.nvidia.com/en-us/support/submit-security-vulnerability/). ## Bias: Field | Response ---------------------------------------------------------------------------------------------------|--------------- Participation considerations from adversely impacted groups [protected classes](https://www.senate.ca.gov/content/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](https://creativecommons.org/licenses/by/4.0/legalcode.en) 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](https://creativecommons.org/licenses/by/4.0/legalcode.en) 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.