Duplicate from nvidia/parakeet-rnnt-1.1b

Co-authored-by: Nithin Rao Koluguri <nithinraok@users.noreply.huggingface.co>

.eval_results/open_asr_leaderboard.yaml

@@ -0,0 +1,99 @@
+- dataset:
+    id: hf-audio/open-asr-leaderboard
+    task_id: mean_wer
+  value: 7.12375
+  date: '2023-12-27'
+  source:
+    url: https://huggingface.co/hf-audio
+    name: open-asr-leaderboard
+    user: hf-audio
+
+- dataset:
+    id: hf-audio/open-asr-leaderboard
+    task_id: rtfx
+  value: 2053.14697
+  date: '2023-12-27'
+  source:
+    url: https://huggingface.co/hf-audio
+    name: open-asr-leaderboard
+    user: hf-audio
+
+- dataset:
+    id: hf-audio/open-asr-leaderboard
+    task_id: ami_wer
+  value: 17.01
+  date: '2023-12-27'
+  source:
+    url: https://huggingface.co/hf-audio
+    name: open-asr-leaderboard
+    user: hf-audio
+
+- dataset:
+    id: hf-audio/open-asr-leaderboard
+    task_id: earnings22_wer
+  value: 13.94
+  date: '2023-12-27'
+  source:
+    url: https://huggingface.co/hf-audio
+    name: open-asr-leaderboard
+    user: hf-audio
+
+- dataset:
+    id: hf-audio/open-asr-leaderboard
+    task_id: gigaspeech_wer
+  value: 9.89
+  date: '2023-12-27'
+  source:
+    url: https://huggingface.co/hf-audio
+    name: open-asr-leaderboard
+    user: hf-audio
+
+- dataset:
+    id: hf-audio/open-asr-leaderboard
+    task_id: librispeech_clean_wer
+  value: 1.45
+  date: '2023-12-27'
+  source:
+    url: https://huggingface.co/hf-audio
+    name: open-asr-leaderboard
+    user: hf-audio
+
+- dataset:
+    id: hf-audio/open-asr-leaderboard
+    task_id: librispeech_other_wer
+  value: 2.5
+  date: '2023-12-27'
+  source:
+    url: https://huggingface.co/hf-audio
+    name: open-asr-leaderboard
+    user: hf-audio
+
+- dataset:
+    id: hf-audio/open-asr-leaderboard
+    task_id: spgispeech_wer
+  value: 2.93
+  date: '2023-12-27'
+  source:
+    url: https://huggingface.co/hf-audio
+    name: open-asr-leaderboard
+    user: hf-audio
+
+- dataset:
+    id: hf-audio/open-asr-leaderboard
+    task_id: tedlium_wer
+  value: 3.83
+  date: '2023-12-27'
+  source:
+    url: https://huggingface.co/hf-audio
+    name: open-asr-leaderboard
+    user: hf-audio
+
+- dataset:
+    id: hf-audio/open-asr-leaderboard
+    task_id: voxpopuli_wer
+  value: 5.44
+  date: '2023-12-27'
+  source:
+    url: https://huggingface.co/hf-audio
+    name: open-asr-leaderboard
+    user: hf-audio

.gitattributes

@@ -0,0 +1,36 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+parakeet-rnnt-1.1b.nemo filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,419 @@
+---
+language:
+- en
+library_name: nemo
+datasets:
+- librispeech_asr
+- fisher_corpus
+- Switchboard-1
+- WSJ-0
+- WSJ-1
+- National-Singapore-Corpus-Part-1
+- National-Singapore-Corpus-Part-6
+- vctk
+- voxpopuli
+- europarl
+- multilingual_librispeech
+- mozilla-foundation/common_voice_8_0
+- MLCommons/peoples_speech
+thumbnail: null
+tags:
+- automatic-speech-recognition
+- speech
+- audio
+- Transducer
+- FastConformer
+- Conformer
+- pytorch
+- NeMo
+- hf-asr-leaderboard
+- transformers
+license: cc-by-4.0
+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_rnnt_1.1b
+  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: 17.10
+  - 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: 14.11
+  - 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: 9.96
+  - 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: 1.46
+  - 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: 2.47
+  - 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: 3.11
+  - 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: 3.92
+  - 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: 5.39
+  - task:
+      type: Automatic Speech Recognition
+      name: automatic-speech-recognition
+    dataset:
+      name: Mozilla Common Voice 9.0
+      type: mozilla-foundation/common_voice_9_0
+      config: en
+      split: test
+      args:
+        language: en
+    metrics:
+    - name: Test WER
+      type: wer
+      value: 5.79
+  
+metrics:
+- wer
+pipeline_tag: automatic-speech-recognition
+---
+
+# Parakeet RNNT 1.1B (en)
+
+<style>
+img {
+ display: inline;
+}
+</style>
+
+[![Model architecture](https://img.shields.io/badge/Model_Arch-FastConformer--Transducer-lightgrey#model-badge)](#model-architecture)
+| [![Model size](https://img.shields.io/badge/Params-1.1B-lightgrey#model-badge)](#model-architecture)
+| [![Language](https://img.shields.io/badge/Language-en-lightgrey#model-badge)](#datasets)
+
+
+`parakeet-rnnt-1.1b` is an ASR model that transcribes speech in lower case English alphabet. This model is jointly developed by [NVIDIA NeMo](https://github.com/NVIDIA/NeMo) and [Suno.ai](https://www.suno.ai/) teams.
+It is an XXL version of FastConformer Transducer [1] (around 1.1B parameters) model.
+See the [model architecture](#model-architecture) section and [NeMo documentation](https://docs.nvidia.com/deeplearning/nemo/user-guide/docs/en/main/asr/models.html#fast-conformer) for complete architecture details.
+
+## Licence/Terms Of Use
+
+License to use this model is covered by the [CC-BY-4.0](https://creativecommons.org/licenses/by/4.0/). By downloading the public and release version of the model, you accept the terms and conditions of the [CC-BY-4.0](https://creativecommons.org/licenses/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](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.<br>
+
+### Explore more from NVIDIA:  <br>
+What is [Nemotron](https://www.nvidia.com/en-us/ai-data-science/foundation-models/nemotron/)?<br>
+NVIDIA Developer [Nemotron](https://developer.nvidia.com/nemotron)<br>
+[NVIDIA Riva Speech](https://developer.nvidia.com/riva?sortBy=developer_learning_library%2Fsort%2Ffeatured_in.riva%3Adesc%2Ctitle%3Aasc#demos)<br>
+[NeMo Documentation](https://docs.nvidia.com/nemo-framework/user-guide/latest/nemotoolkit/asr/models.html)<br>
+
+## How to Use this Model
+
+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.
+
+You can also run Parakeet RNNT with [Transformers](https://github.com/huggingface/transformers) 🤗 (more below).
+
+### 1) NeMo usage
+
+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.
+```
+pip install nemo_toolkit['all']
+``` 
+
+#### Automatically instantiate the model
+
+```python
+import nemo.collections.asr as nemo_asr
+asr_model = nemo_asr.models.EncDecRNNTBPEModel.from_pretrained(model_name="nvidia/parakeet-rnnt-1.1b")
+```
+
+#### Transcribing using Python
+First, let's get a sample
+```
+wget https://dldata-public.s3.us-east-2.amazonaws.com/2086-149220-0033.wav
+```
+Then simply do:
+```
+output = asr_model.transcribe(['2086-149220-0033.wav'])
+print(output[0].text)
+```
+
+#### Transcribing many audio files
+
+```shell
+python [NEMO_GIT_FOLDER]/examples/asr/transcribe_speech.py 
+ pretrained_name="nvidia/parakeet-rnnt-1.1b" 
+ audio_dir="<DIRECTORY CONTAINING AUDIO FILES>"
+```
+
+### 2) [Transformers](https://github.com/huggingface/transformers) 🤗 usage 
+
+
+Parakeet RNNT is available in 🤗 Transformers starting from v5.13.0.
+
+```bash
+pip install "transformers>=5.13.0"
+```
+
+<details>
+  <summary>➡️ Pipeline usage</summary>
+
+```python
+from transformers import pipeline
+
+pipe = pipeline("automatic-speech-recognition", model="nvidia/parakeet-rnnt-1.1b")
+out = pipe("https://huggingface.co/datasets/hf-internal-testing/dummy-audio-samples/resolve/main/bcn_weather.mp3")
+print(out)
+```
+</details>
+
+<details>
+  <summary>➡️ AutoModel</summary>
+
+```python
+from transformers import AutoModelForRNNT, AutoProcessor
+from datasets import load_dataset, Audio
+
+num_samples = 3
+
+model_id = "nvidia/parakeet-rnnt-1.1b"
+processor = AutoProcessor.from_pretrained(model_id)
+model = AutoModelForRNNT.from_pretrained(model_id, dtype="auto", device_map="auto")
+
+ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
+ds = ds.cast_column("audio", Audio(sampling_rate=processor.feature_extractor.sampling_rate))
+speech_samples = [el["array"] for el in ds["audio"][:num_samples]]
+
+inputs = processor(speech_samples, sampling_rate=processor.feature_extractor.sampling_rate)
+inputs.to(model.device, dtype=model.dtype)
+output = model.generate(**inputs, return_dict_in_generate=True)
+print(processor.decode(output.sequences, skip_special_tokens=True))
+```
+</details>
+
+
+<details>
+  <summary>➡️ Timestamping</summary>
+
+```python
+from datasets import Audio, load_dataset
+from transformers import AutoModelForRNNT, AutoProcessor
+
+num_samples = 3
+
+model_id = "nvidia/parakeet-rnnt-1.1b"
+processor = AutoProcessor.from_pretrained(model_id)
+model = AutoModelForRNNT.from_pretrained(model_id, dtype="auto", device_map="auto")
+
+ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
+ds = ds.cast_column("audio", Audio(sampling_rate=processor.feature_extractor.sampling_rate))
+speech_samples = [el["array"] for el in ds["audio"][:num_samples]]
+
+inputs = processor(speech_samples, sampling_rate=processor.feature_extractor.sampling_rate)
+inputs.to(model.device, dtype=model.dtype)
+output = model.generate(**inputs, return_dict_in_generate=True)
+decoded_output, decoded_timestamps = processor.decode(
+    output.sequences,
+    durations=output.durations,
+    skip_special_tokens=True,
+)
+print("Transcription:", decoded_output)
+print("Timestamped tokens:", decoded_timestamps)
+```
+</details>
+
+<details>
+  <summary>➡️ Training</summary>
+
+```python
+from transformers import AutoModelForRNNT, AutoProcessor
+from datasets import load_dataset, Audio
+import torch
+
+model_id = "nvidia/parakeet-rnnt-1.1b"
+NUM_SAMPLES = 4
+
+processor = AutoProcessor.from_pretrained(model_id)
+model = AutoModelForRNNT.from_pretrained(model_id, dtype=torch.bfloat16, device_map="auto")
+model.train()
+
+ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
+ds = ds.cast_column("audio", Audio(sampling_rate=processor.feature_extractor.sampling_rate))
+speech_samples = [el["array"] for el in ds["audio"][:NUM_SAMPLES]]
+text_samples = ds["text"][:NUM_SAMPLES]
+
+# passing `text` to the processor will prepare inputs' `labels` key
+inputs = processor(audio=speech_samples, text=text_samples, sampling_rate=processor.feature_extractor.sampling_rate)
+inputs.to(device=model.device, dtype=model.dtype)
+
+outputs = model(**inputs)
+print("Loss:", outputs.loss.item())
+outputs.loss.backward()
+```
+</details>
+
+For more details about usage, please refer to the [Transformers' documentation](https://huggingface.co/docs/transformers/en/model_doc/parakeet).
+
+### Input
+
+This model accepts 16000 Hz mono-channel audio (wav files) as input.
+
+### Output
+
+This model provides transcribed speech as a string for a given audio sample.
+
+## Model Architecture
+
+FastConformer [1] is an optimized version of the Conformer model with 8x depthwise-separable convolutional downsampling. The model is trained in a multitask setup with a Transducer decoder (RNNT) loss. You may find more information on the details of FastConformer here: [Fast-Conformer Model](https://docs.nvidia.com/deeplearning/nemo/user-guide/docs/en/main/asr/models.html#fast-conformer).
+
+## Training
+
+The NeMo toolkit [3] was used for training the models for over several hundred epochs. These model are trained with this [example script](https://github.com/NVIDIA/NeMo/blob/main/examples/asr/asr_transducer/speech_to_text_rnnt_bpe.py) and this [base config](https://github.com/NVIDIA/NeMo/blob/main/examples/asr/conf/fastconformer/fast-conformer_transducer_bpe.yaml).
+
+The tokenizers for these models were built using the text transcripts of the train set with this [script](https://github.com/NVIDIA/NeMo/blob/main/scripts/tokenizers/process_asr_text_tokenizer.py).
+
+### Datasets
+
+The model was trained on 64K hours of English speech collected and prepared by NVIDIA NeMo and Suno teams.
+
+The training dataset consists of private subset with 40K hours of English speech plus 24K hours from the following public datasets:
+
+- Librispeech 960 hours of English speech
+- Fisher Corpus
+- Switchboard-1 Dataset
+- WSJ-0 and WSJ-1
+- National Speech Corpus (Part 1, Part 6)
+- VCTK
+- VoxPopuli (EN)
+- Europarl-ASR (EN)
+- Multilingual Librispeech (MLS EN) - 2,000 hour subset
+- Mozilla Common Voice (v7.0)
+- People's Speech  - 12,000 hour subset
+
+## Performance
+
+The performance of Automatic Speech Recognition models is measuring using Word Error Rate. Since this dataset is trained on multiple domains and a much larger corpus, it will generally perform better at transcribing audio in general.
+
+The following tables summarizes the performance of the available models in this collection with the Transducer decoder. Performances of the ASR models are reported in terms of Word Error Rate (WER%) with greedy decoding. 
+
+|**Version**|**Tokenizer**|**Vocabulary Size**|**AMI**|**Earnings-22**|**Giga Speech**|**LS test-clean**|**SPGI Speech**|**TEDLIUM-v3**|**Vox Populi**|**Common Voice**|
+|---------|-----------------------|-----------------|---------------|---------------|------------|-----------|-----|-------|------|------|
+| 1.22.0  | SentencePiece Unigram | 1024 | 17.10 | 14.11 | 9.96 | 1.46 | 2.47 | 3.11 | 3.92 | 5.39 | 5.79 |
+
+These are greedy WER numbers without external LM. More details on evaluation can be found at [HuggingFace ASR Leaderboard](https://huggingface.co/spaces/hf-audio/open_asr_leaderboard)
+
+## NVIDIA Riva: Deployment
+
+[NVIDIA Riva](https://developer.nvidia.com/riva), is an accelerated speech AI SDK deployable on-prem, in all clouds, multi-cloud, hybrid, on edge, and embedded. 
+Additionally, Riva provides: 
+
+* World-class out-of-the-box accuracy for the most common languages with model checkpoints trained on proprietary data with hundreds of thousands of GPU-compute hours 
+* Best in class accuracy with run-time word boosting (e.g., brand and product names) and customization of acoustic model, language model, and inverse text normalization 
+* Streaming speech recognition, Kubernetes compatible scaling, and enterprise-grade support 
+
+Although this model isn’t supported yet by Riva, the [list of supported models is here](https://huggingface.co/models?other=Riva).  
+Check out [Riva live demo](https://developer.nvidia.com/riva#demos). 
+
+## References
+[1] [Fast Conformer with Linearly Scalable Attention for Efficient Speech Recognition](https://arxiv.org/abs/2305.05084)
+
+[2] [Google Sentencepiece Tokenizer](https://github.com/google/sentencepiece)
+
+[3] [NVIDIA NeMo Toolkit](https://github.com/NVIDIA/NeMo)
+
+[4] [Suno.ai](https://suno.ai/)
+
+[5] [HuggingFace ASR Leaderboard](https://huggingface.co/spaces/hf-audio/open_asr_leaderboard)
+
+

config.json

@@ -0,0 +1,42 @@
+{
+  "architectures": [
+    "ParakeetForRNNT"
+  ],
+  "blank_token_id": 1024,
+  "decoder_hidden_size": 640,
+  "dtype": "float32",
+  "encoder_config": {
+    "activation_dropout": 0.1,
+    "attention_bias": true,
+    "attention_dropout": 0.1,
+    "conv_kernel_size": 9,
+    "convolution_bias": true,
+    "dropout": 0.1,
+    "dropout_positions": 0.0,
+    "hidden_act": "silu",
+    "hidden_size": 1024,
+    "initializer_range": 0.02,
+    "intermediate_size": 4096,
+    "layerdrop": 0.1,
+    "max_position_embeddings": 5000,
+    "model_type": "parakeet_encoder",
+    "num_attention_heads": 8,
+    "num_hidden_layers": 42,
+    "num_key_value_heads": 8,
+    "num_mel_bins": 80,
+    "scale_input": true,
+    "subsampling_conv_channels": 256,
+    "subsampling_conv_kernel_size": 3,
+    "subsampling_conv_stride": 2,
+    "subsampling_factor": 8
+  },
+  "hidden_act": "relu",
+  "initializer_range": 0.02,
+  "is_encoder_decoder": true,
+  "max_symbols_per_step": 10,
+  "model_type": "parakeet_rnnt",
+  "num_decoder_layers": 2,
+  "pad_token_id": 0,
+  "transformers_version": "5.13.0.dev0",
+  "vocab_size": 1025
+}

generation_config.json

@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "decoder_start_token_id": 1024,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "pad_token_id": 0,
+  "transformers_version": "5.13.0.dev0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09ae8537c649f096be2ffc6ec466e4e813c5e319da7430bdb0304bc5817ff7ac
+size 4282269868

parakeet-rnnt-1.1b.nemo

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:535896f014953d945b287ac533560e20da8103c6781b152de4645528e2b60738
+size 4283105280

processor_config.json

@@ -0,0 +1,17 @@
+{
+  "blank_token": "<blank>",
+  "decoder_type": "rnnt",
+  "feature_extractor": {
+    "feature_extractor_type": "ParakeetFeatureExtractor",
+    "feature_size": 80,
+    "hop_length": 160,
+    "n_fft": 512,
+    "padding_side": "right",
+    "padding_value": 0.0,
+    "preemphasis": 0.97,
+    "return_attention_mask": true,
+    "sampling_rate": 16000,
+    "win_length": 400
+  },
+  "processor_class": "ParakeetProcessor"
+}

tokenizer_config.json

@@ -0,0 +1,9 @@
+{
+  "backend": "tokenizers",
+  "clean_up_tokenization_spaces": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<blank>",
+  "processor_class": "ParakeetProcessor",
+  "tokenizer_class": "ParakeetTokenizer",
+  "unk_token": "<unk>"
+}