alt.freeweights.speech / nb-whisper-small
From: NbAiLab <huggingface.co/NbAiLab>Newsgroups: alt.freeweights.speechSubject:

nb-whisper-small

Date: 2026-11-15Commit: e9bb5cbSigned: 2DC28CC7B26A283B ✓

Automatic speech recognition model with 242M parameters. Ctranslate2 and ggml and onnx and safetensors weights, 7.44 GB in all. Published by NbAiLab under Apache-2.0.

242M params7.44GBnb-whisper-smallctranslate2 ggml onnx safetensorspermissive
FactsParams242MSize7.44 GBFormatsctranslate2, ggml, onnx, safetensorsTaskautomatic speech recognitionLicenseApache-2.0From sourcepermissive
$ fw get NbAiLab/nb-whisper-small
# manifest sha256 eb86da2fccea… · 7.44 GB · 67 files
$ fw verify ./nb-whisper-small NbAiLab/nb-whisper-small
From sourceHosted (signed)NbAiLab/nb-whisper-smallLast check: 2026-11-15 04:57 UTC

Get help: custom fine-tune or private deploy. We review your setup before we quote.

Quantized of whisper-small.

Works with

Overview

Size
7.44 GB
Weights
967 MB (safetensors)
Parameters
242M
Formats
ctranslate2, ggml, onnx, safetensors
Task
automatic speech recognition
License
Apache-2.0 (permissive)
Files
67, each with a sha256
Publisher
NbAiLab
Added
2026-11-15
Section
alt.freeweights.speech
Lineage

Original release from the publisher.

Base model: openai/whisper-small

Where these bytes come from
Publisher at the pinned commit→You

Sources are tried in order. A file counts only when its size and sha256 match the manifest. Sources are checked when you ask for them, not on a timer.

Sources
BadgeHostLast checkResult
From sourcehuggingface.co2026-11-15 04:57 UTCpassed

Model card

From the publisher at commit e9bb5cb. Shown as plain text with links; images open at the publisher.

NB-Whisper Small#

Introducing the Norwegian NB-Whisper Small model, proudly developed by the National Library of Norway. NB-Whisper is a cutting-edge series of models designed for automatic speech recognition (ASR) and speech translation. These models are based on the work of OpenAI's Whisper. Each model in the series has been trained for 250,000 steps, utilizing a diverse dataset of 8 million samples. These samples consist of aligned audio clips, each 30 seconds long, culminating in a staggering 66,000 hours of speech. For an in-depth understanding of our training methodology and dataset composition, keep an eye out for our upcoming article.

Model SizeParametersModel
Tiny39MNB-Whisper Tiny
Base74MNB-Whisper Base
Small244MNB-Whisper Small
Medium769MNB-Whisper Medium
Large1550MNB-Whisper Large
Verbatim Model#

While the main models are suitable for most transcription task, we demonstrate how easy it is to change the output of the main model. The following models are trained 250 additional steps from the main models above, and might be suitable for more targetted use cases:

  • Verbatim version: This lower-cased variant is more literal and suitable for tasks requiring detailed transcription, such as linguistic analysis.
Model SizeParametersSemantic version
Tiny39MTiny - semantic
Base74MBase - semantic
Small244MSmall - semantic
Medium769MMedium - semantic
Large1550MLarge - semantic
Model Description#

How to Use the Models#

Online Demos#

You can try the models directly through the HuggingFace Inference API, accessible on the right side of this page. Be aware that initially, the model needs to load and will run on limited CPU capacity, which might be slow. To enhance your experience, we are temporarily hosting some models on TPUs for a few days, significantly boosting their performance. Explore these under the Spaces section on the Main Page.

Local Setup with HuggingFace#

Alternatively, you can run the models locally. The Tiny, Base, and Small models are optimized for CPU execution. For the Medium and Large models, we recommend a system equipped with a GPU to ensure efficient processing. Setting up and using these models with HuggingFace's Transformers is straightforward, provided you have Python installed on your machine. For practical demonstrations, refer to examples using this sample mp3 file.

# Download the sample file
$ wget -N https://github.com/NbAiLab/nb-whisper/raw/main/audio/king.mp3

# Install necessary libraries. 
$ pip install transformers>=4.35.2

After this is done, you should be able to run this in Python:

from transformers import pipeline

# Load the model
asr = pipeline("automatic-speech-recognition", "NbAiLabBeta/nb-whisper-small")

#transcribe
asr("king.mp3", generate_kwargs={'task': 'transcribe', 'language': 'no'})

Expected output

{
  {'text': ' Nordmenn er nordlendinger, trøndere, sørlendinger og folk fra alle andre regioner. Nordmenn er også innvandret fra Afghanistan, Pakistan, Polen, Sverige, Somalia og Syria. Det er ikke alltid så lett å si hvor vi er fra, hvilken nasjonalitet vi er fra. Hvilken nasjonalitet vi er fra. Hvilken nasjonalitet vi er fra. Hvilken nasjonalitet vi er fra. Hvilken nasjonalitet vi er fra. Hvilken nasjonalitet vi er fra. Hvilken nasjonalitet vi er fra.'}
}
Extended HuggingFace#

Examining the output above, we see that there are multiple repetitions at the end. This is because the video is longer than 30 seconds. By passing the chunk_lengt_s argument, we can transcribe longer file. Our experience is that we get slightly better result by setting that to 28 seconds instead of the default 30 seconds. We also recommend setting the beam size to 5 if possible. This greatly increases the accuracy but takes a bit longer and requires slightly more memory. The examples below also illustrates how to transcribe to English or Nynorsk, and how to get timestamps for sentences and words.

# Long Transcripts
asr("king.mp3", chunk_length_s=28, generate_kwargs={'task': 'transcribe', 'language': 'no'})

# Increase accuracy by setting beam size to 5
asr("king.mp3", chunk_length_s=28, return_timestamps=True, generate_kwargs={'num_beams': 5, 'task': 'transcribe', 'language': 'no'})

# Return Timestamps
asr("king.mp3", chunk_length_s=28, return_timestamps=True, generate_kwargs={'task': 'transcribe', 'language': 'no'})

# Return Word Level Timestamps
asr("king.mp3", chunk_length_s=28, return_timestamps="word", generate_kwargs={'task': 'transcribe', 'language': 'no'})

# Transcribe to Nynorsk
asr("king.mp3", chunk_length_s=28, generate_kwargs={'task': 'transcribe', 'language': 'nn'})

# Transcribe to English
asr("king.mp3", chunk_length_s=28, generate_kwargs={'task': 'transcribe', 'language': 'en'})

Expected output

Long transcripts:

{
  {'text': ' Nordmenn er nordlendinger, trøndere, sørlendinger og folk fra alle andre regioner. Nordmenn er også innvandret fra Afghanistan, Pakistan, Polen, Sverige, Somalia og Syria. Det er ikke alltid så lett å si hvor vi er fra, hvilken nasjonalitet vi er fra. Hvilken nasjonalitet vi er fra. Hvilken nasjonalitet vi er fra. Hvilken nasjonalitet vi er fra. Hvilken nasjonalitet vi er fra. Hvilken nasjonalitet vi er fra, hvilken nasjonalitet vi tilhører. Det vi kaller hjem, er der hjertet vårt er, og det kan ikke alltid plasseres innenfor landegrenser. Nordmenn er jenter som er glad i jenter, gutter som er glad i gutter, og jenter og gutter som er glad i hverandre. Nordmenn trommer på Gud, Allah, Altet og ingenting. Nordmenn liker Grieg, Kygo, Helbilis og Kari Bremnes. Med andre ord, Norge er dere. Norge er oss. Mitt største håp for Norge er at vi skal klare å ta vare på hverandre, at vi skal bygge dette landet videre på tillit, fellesskap og raushet.'}
}

Timestamps:

{
  {'text': ' Nordmenn er nordlendinger, trøndere, sørlendinger og folk fra alle andre regioner. Nordmenn er også innvandret fra Afghanistan, Pakistan, Polen, Sverige, Somalia og Syria. Det er ikke alltid så lett å si hvor vi er fra, hvilken nasjonalitet vi er fra. Hvilken nasjonalitet vi er fra. hvilken nasjonalitet vi tilhører. Det vi kaller hjem, er der hjertet vårt er, og det kan ikke alltid plasseres innenfor landegrenser. Nordmenn er jenter som er glad i jenter, gutter som er glad i gutter, og jenter og gutter som er glad i hverandre. Nordmenn trommer på Gud, Allah, Altet og ingenting. Nordmenn liker Grieg, Kygo, Helbiles og Kari Bremnes. Med andre ord, Norge er dere. Norge er oss. Mitt største håp for Norge er at vi skal klare å ta vare på hverandre, at vi skal bygge dette landet videre på tillit, fellesskap og raushet.',
 'chunks': [{'timestamp': (0.0, 5.46),
   'text': ' Nordmenn er nordlendinger, trøndere, sørlendinger'},
  {'timestamp': (5.52, 8.68), 'text': ' og folk fra alle andre regioner.'},
  {'timestamp': (8.68, 16.64),
   'text': ' Nordmenn er også innvandret fra Afghanistan, Pakistan, Polen, Sverige, Somalia og Syria.'},
  {'timestamp': (16.64, 13.3),
   'text': ' Det er ikke alltid så lett å si hvor vi er fra, hvilken nasjonalitet vi er fra.'},
  {'timestamp': (13.32, 30.28),
   'text': ' Hvilken nasjonalitet vi er fra. hvilken nasjonalitet vi tilhører.'},
  {'timestamp': (32.52, 39.16),
   'text': ' Det vi kaller hjem, er der hjertet vårt er, og det kan ikke alltid plasseres'},
  {'timestamp': (39.16, 42.0), 'text': ' innenfor landegrenser.'},
  {'timestamp': (42.0, 46.74),
   'text': ' Nordmenn er jenter som er glad i jenter, gutter som er glad i gutter,'},
  {'timestamp': (46.74, 51.12),
   'text': ' og jenter og gutter som er glad i hverandre.'},
  {'timestamp': (51.16, 57.42),
   'text': ' Nordmenn trommer på Gud, Allah, Altet og ingenting.'},
  {'timestamp': (57.42, 64.3),
   'text': ' Nordmenn liker Grieg, Kygo, Helbiles og Kari Bremnes.'},
  {'timestamp': (64.34, 71.24),
   'text': ' Med andre ord, Norge er dere. Norge er oss.'},
  {'timestamp': (71.24, 78.04),
   'text': ' Mitt største håp for Norge er at vi skal klare å ta vare på hverandre,'},
  {'timestamp': (78.12, 84.68),
   'text': ' at vi skal bygge dette landet videre på tillit, fellesskap og raushet.'}]}
}

Word Level Timestamps:

{
  {"text": "Nordmenn er nordlendinger, trøndere, sørlendinger og folk fra alle andre regioner. Nordmenn er også innvandret fra Afghanistan, Pakistan, Polen, Sverige, Somalia og Syria. Det er ikke alltid så lett å si hvor vi er fra, hvilken nasjonalitet vi tilhører. Det vi kaller hjem, er der hjertet vårt er, og det kan ikke alltid plasseres innenfor landegrenser. Nordmenn er jenter som er glad i jenter, gutter som er glad i gutter, og jenter og gutter som er glad i hverandre. Nordmenn trommer på Gud, Allah, Altet og ingenting. Nordmenn liker Grieg, Kygo, Helbilis og Kari Bremnes. Med andre ord, Norge er dere. Norge er oss. Mitt største håp for Norge er at vi skal klare å ta vare på hverandre, at vi skal bygge dette landet videre på tillit, fellesskap og raushet.",
  "chunks": [
    {"text": "Nordmenn", "timestamp": [0.72, 1.42]},
    {"text": "er", "timestamp": [1.42, 1.74]},
    // ... more chunks ...
    {"text": "raushet.", "timestamp": [83.1, 84.88]}
  ]
  }
}

Nynorsk:

{
  {"text": "Nordmenn er nordlendingar, trøndarar, sørlendingar og folk frå alle andre regionar. Nordmenn er også innvandra frå Afghanistan, Pakistan, Polen, Sverige, Somalia og Syria. Det er ikkje alltid så lett å seie kvar vi er frå, kva nasjonalitet vi tilhøyrer. Det vi kallar heim, er der hjartet vårt er, og det kan ikkje alltid plasserast innanfor landegrenser. Nordmenn er jenter som er glad i jenter, gutar som erade i gutar, og jenter og gutar som er glade i kvarandre. Nordmenn trommar på Gud, Allah, Altet og ingenting. Nordmenn liker Grieg, Kygo, Helbiles og Kari Bremnes. Med andre ord, Noreg er dere! Noreg er oss. Mitt største håp for Noreg er at vi skal klare å ta vare på kvarandre, at vi skal byggje dette landet vidare på tillit, fellesskap og raushet."}
}

English:

{
  {"text": "Norwegians are Norwegians, trønders, southerners and people from all other regions. Norwegians are also invaded from Afghanistan, Pakistan, Poland, Sweden, Somalia and Suria. It is not always so easy to say where we are from, what nationality we belong to. What we call home is where our heart is, and it cannot always be placed within national borders. Norwegians are girls who like girls, boys who like boys, and girls and boys who like each other. Norwegians thrump on God, Allah, Altet and nothing. Norwegians like Grieg, Kygo, Helbilis and Kari Bremnes. In other words, Norway is you. Norway is us. My biggest hope for Norway is that we should be able to take care of each other, that we should build this country on trust, community and generosity."}
}
Whisper CPP#

Whisper CPP is a C++ implementation of the Whisper model, offering the same functionalities with the added benefits of C++ efficiency and performance optimizations. This allows embedding any Whisper model into a binary file, facilitating the development of real applications. However, it requires some familiarity with compiling C++ programs. Their homepage provides examples of how to build applications, including real-time transcription.

We have converted this model to the ggml-format model used by Whisper CPP binaries. The file can be downloaded here, and a q5_0 quantized version is also available here.

# We can download and compile whisper.cpp
$ git clone --depth 1 https://github.com/ggerganov/whisper.cpp --branch v1.5.1
$ cd whisper.cpp/
$ make

# We also need to convert the audio to WAV as that is the only format supported by whisper.cpp
$ wget -N https://github.com/NbAiLab/nb-whisper/raw/main/audio/king.mp3
$ ffmpeg -i king.mp3 -ar 16000 -ac 1 -c:a pcm_s16le king.wav                                        

# Lets download the two ggml-files from this site
wget -N https://huggingface.co/NbAiLab/nb-whisper-small/resolve/main/ggml-model.bin -O models/nb-small-ggml-model.bin
wget -N https://huggingface.co/NbAiLab/nb-whisper-small/resolve/main/ggml-model-q5_0.bin -O models/nb-small-ggml-model-q5_0.bin

# And run it with the f16 default model
$ ./main -l no -m models/nb-small-ggml-model.bin king.wav

# Or the quantized version
$ ./main -l no -m models/nb-small-ggml-model-q5_0.bin king.wav
WhisperX and Speaker Diarization#

Speaker diarization is a technique in natural language processing and automatic speech recognition that identifies and separates different speakers in an audio recording. It segments the audio into parts based on who is speaking, enhancing the quality of transcribing meetings or phone calls. We find that WhisperX is the easiest way to use our models for diarizing speech. In addition, WhisperX is using phoneme-based Wav2Vec-models for improving the alignment of the timestamps. As of December 2023 it also has native support for using the nb-wav2vec-models. It currently uses PyAnnote-audio for doing the actual diarization. This package has a fairly strict licence where you have to agree to user terms. Follow the instructions below.

# Follow the install instructions on https://github.com/m-bain/whisperX
# Make sure you have a HuggingFace account and have agreed to the pyannote terms

# Log in (or supply HF Token in command line)
huggingface-cli login

# Download a test file
wget -N https://github.com/NbAiLab/nb-whisper/raw/main/audio/knuthamsun.mp3

# Optional. If you get complains about not support for Norwegian, do:
pip uninstall whisperx && pip install git+https://github.com/m-bain/whisperx.git@8540ff5985fceee764acbed94f656063d7f56540

# Transcribe the test file. All transcripts will end up in the directory of the mp3-file
whisperx knuthamsun.mp3 --model NbAiLabBeta/nb-whisper-small --language no --diarize

You can also run WhisperX from Python. Please take a look at the instructions on WhisperX homepage.

API#

Instructions for accessing the models via a simple API are included in the demos under Spaces. Note that these demos are temporary and will only be available for a few weeks.

Training Data#

The training data originates from Språkbanken and the National Library of Norway's digital collection, including:

  • NST Norwegian ASR Database (16 kHz) and its corresponding dataset
  • Transcribed speeches from the Norwegian Parliament by Språkbanken
  • TV broadcast (NRK) subtitles (NLN digital collection)
  • Audiobooks (NLN digital collection)

Downstream Use#

The models, especially the smaller ones, may exhibit occasional hallucinations and may drop parts of the transcript. They are designed to convert spoken language into grammatically correct written sentences, which might not always be word-for-word translations. We have made two extra model variant for users that want a different transcription style. We encourage users to try the models themselves to get a better understanding.

Bias, Risks, and Limitations#

Using these models without adequate risk assessment and mitigation could be considered irresponsible. They may contain biases or other undesirable distortions. Users who deploy these models or integrate them into systems or services are responsible for mitigating risks and complying with applicable AI regulations. The National Library of Norway, as the model owner, disclaims liability for any outcomes resulting from third-party use of these models.

Software#

The model was trained using Jax/Flax and converted to PyTorch, Tensorflow, whisper.cpp, and ONXX formats. These are available under Files and versions. We welcome requests for conversion to other formats. All training code and scripts are released under the Apache License 2.0 in the GitHub repository nb-whisper.

Citation & Contributors#

The NB-Whisper Small model is a product of the NoSTram project led by Per Egil Kummervold (@pere) at the National Library of Norway. Key contributors include Javier de la Rosa (@versae), Freddy Wetjen (@freddyw), and Rolv-Arild Braaten (@Rolv-Arild). NB AI-Lab, under the direction of Svein Arne Brygfjeld (@Brygfjeld), supported the project's successful completion. A detailed paper on our process and findings is forthcoming.

Disclaimer#

The models published in this repository are intended for a generalist purpose and are available to third parties. These models may have bias and/or any other undesirable distortions. When third parties, deploy or provide systems and/or services to other parties using any of these models (or using systems based on these models) or become users of the models, they should note that it is their responsibility to mitigate the risks arising from their use and, in any event, to comply with applicable regulations, including regulations regarding the use of artificial intelligence. In no event shall the owner of the models (The National Library of Norway) be liable for any results arising from the use made by third parties of these models.

Acknowledgements#

Our gratitude extends to Google TPU Research Cloud for training resources, Google Cloud for translation credits, and HuggingFace's Sanchit Ghandi for technical support. A special thank you to Per Erik Solberg at Språkbanken for the collaboration on the Stortinget corpus.

Contact#

For feedback, technical concerns, or collaboration inquiries, please contact ailab@nb.no. If you plan to include this model in your research, contact us for the latest information on our upcoming paper for citation purposes.

Files

67 files · 7.44 GBWeights 967 MB (safetensors). Sizes and sha256 from the signed manifest.
Show all 67 files with their sha256
FileSizesha256
.gitattributes1.61 KB50028c997e612f2373f076bde8d0e3ba1a63ef09353ac4620067248dbfa8aba1
README.md20.3 KBc3051e53f686ac892a144b808817b526c4b2f58c6c9c9c89bc9cb0a35687c541
added_tokens.json34.6 KB9715fd2243b6f06a5858b5e32950d2853f73dd5bc201aafcf76f5082a2d8acd1
config.json4.59 KB51c48f695e0d9f23d5651fb3c41d9e21b97efcdd58140032965f3026144a21cd
config_hf.json2.24 KBf71f3b3e85e24431dedf33a33d053baed98ddfd6aadd987580c708ccb2a248ab
ct2/config.json2.37 KBb55496ac7940a7ae47d2c01eab40edfd8701feec1229d9cce3b40014383fb828
ct2/model.bin967 MBc16263d0dbbbd8a486899ab2375fbe67f29f0356d40180ac8ce2443c19a908f0
ct2/vocabulary.json1.07 MB5ad28279db5e546349708b9a74736e2c018737ac5a600f1048f1f26c99b85b47
export_models.sh2.14 KB01cbaa0b45aaa7d863580f177a2cedf70afece258260f1cfe78f7b173bab8175
flax_model.msgpack967 MB9efd6bcd79f353d36ac3402e4f0e52a6ab11d8c0b6266be36f27005ddb1c5a99
generation_config.json3.92 KBf3706d319620c1bb7e787b810b14cc4fda7de0d150272abfe733c089e728a17b
ggml-model-q5_0.bin175 MB2a9025afb6e825fc4ae6a46671e0cb2f43e62f1dec87270deea6fe61b5285a20
ggml-model.bin488 MBa0fc1555f5bd51044b0ea88bb9b7891e1ee331a8087eddb0afc3a05839db48ab
merges.txt494 KB78f27f801feb4283ae969d4cadacb28fc051b655647402b1a252c7079ea11c46
model.bin967 MBc16263d0dbbbd8a486899ab2375fbe67f29f0356d40180ac8ce2443c19a908f0
model.safetensors967 MB72eabc8b35e1a08f19d49554daddc30d98ea11d1eee22c87186fcf4168c86dfe
model_def.json255 Bb1f89b48a0c73323382492b90e993d119e217cfed8c52cd5c82c467902259bef
normalizer.json52.7 KBbf1c507dc8724ca9cf9903640dacfb69dae2f00edee4f21ceba106a7392f26dd
onnx/added_tokens.json34.6 KB9715fd2243b6f06a5858b5e32950d2853f73dd5bc201aafcf76f5082a2d8acd1
onnx/config.json2.25 KB0c11a5769eaa76757603f94353a9d8b27d3f575c036933cc2f96dc897953bf30
onnx/decoder_model.onnx774 MBcd1e9a5c26d65df3f2c1bafbb75f743a7ff080cfc8693661d98434ef91708712
onnx/decoder_with_past_model.onnx717 MB934290a9047badf3e2201af3a74eceb2e54a2b825b9b0202b6a8b94728d8977e
onnx/encoder_model.onnx353 MB07a9eb14450994fba1fa28daaaebc7e50712f1850459a524e09139c698178dbf
onnx/generation_config.json3.92 KBf3706d319620c1bb7e787b810b14cc4fda7de0d150272abfe733c089e728a17b
onnx/merges.txt494 KB78f27f801feb4283ae969d4cadacb28fc051b655647402b1a252c7079ea11c46
onnx/normalizer.json52.7 KBbf1c507dc8724ca9cf9903640dacfb69dae2f00edee4f21ceba106a7392f26dd
onnx/preprocessor_config.json339 Ba6a76d28c93edb273669eb9e0b0636a2bddbb1272c3261e47b7ca6dfdbac1b8d
onnx/special_tokens_map.json2.19 KB4679897a50cc1aea98b7d63b8c928b407f252683d3248add11d091e66cf0d5f1
onnx/tokenizer.json2.48 MB87b38f7a654dbbda293bcdda048d2fb18af241fdd41c62496f8e732209610ec1
onnx/tokenizer_config.json283 KBcbd58e0b0c29af58250917eb9f353c65204a5270b2a8d710f0ec5e3ee1c2b08e
onnx/vocab.json1.04 MB50d6a919f0a0601d56a04eb583c780d18553aa388254ba3158eb6a00f13e2c1a
predictions/validation_clean_stortinget_no/step_0.md123 KB552d6097f74862ade8541ae1520e57e63c43cb990de7c94c94e8a484846595ea
predictions/validation_clean_stortinget_no/step_10000.md122 KB7180efb543cbf48a38cfc7623950d31523194fb8a117508449fb1cd7aec1bfe5
predictions/validation_clean_stortinget_no/step_15000.md122 KB2f2ea0d53552ed513bb877f423cc0ec0ee9c0a643bb86342afb4f2dea8888ee2
predictions/validation_clean_stortinget_no/step_20000.md121 KB92db33290f44edf848073b9a532767a29afe46cc41a0a0c256b257d2f1128d09
predictions/validation_clean_stortinget_no/step_25000.md123 KB7d5f9da2390a0dcd088222ec2d02e0f124d23457e712e19e8672eb63708f34e3
predictions/validation_clean_stortinget_no/step_30000.md123 KBc4412af2d3e77b33169ac9f7c01acdac19420258a44c4d2308f2267010dfb086
predictions/validation_clean_stortinget_no/step_35000.md123 KB86862d165d77e0559e2c5885ee7b48440ba9710e07a57329298e4b68279b475b
predictions/validation_clean_stortinget_no/step_40000.md122 KB42972644393a944bc614b0b183256b0ee93a3258885f9a8db10989268052fe39
predictions/validation_clean_stortinget_no/step_45000.md123 KBcbd76ec55957c1a4945e01a3b79b2fe77ba7fc45fcf9478b3c830c3909ed909d
predictions/validation_clean_stortinget_no/step_49999.md121 KBbb9abb7ad98b0d7f55a22864b57f53745af1475f9d38ee21920adfa45c91bfce
predictions/validation_clean_stortinget_no/step_5000.md122 KBeab1e8370c436aac63542a6a7652b7265d0cde431a9c7fecbc4bbe719c398052
predictions/validation_nst/step_0.md36.8 KB9e374e2377bc59a7550c920c5990d245029a9eeb1c9b187a98fa8647e6949528
predictions/validation_nst/step_10000.md37.0 KB41a8f6b9c1a794f3af06007d472863a82eb3461fb29af5cd09d79a8b6e4ef677
predictions/validation_nst/step_15000.md36.8 KB6e24ee32db4c5084767f7af83c140061562c32cfc5dc8c0342db49573cee0c14
predictions/validation_nst/step_20000.md36.8 KB2051a31a3c7af49281f4bcefa6cdd9fae3ebe89cce8adf563be77e5f4c7fb9c1
predictions/validation_nst/step_25000.md36.8 KB5ea62c7e6be9509e5a8b0fbf86b6082d236a897ca5ca0d7af79177e17eae8f07
predictions/validation_nst/step_30000.md36.8 KBc38ccccabd4f7876dd58130218b4174cec014807208eadc9f2734388c3bd1793
predictions/validation_nst/step_35000.md36.8 KB8d367052f697381b226ff339c0b43ea4f7ce9cb9753d26bd5587ae109bba1e18
predictions/validation_nst/step_40000.md36.8 KB0e77ea0988a7a50bb86b8fc5aa875de53dd3ec147c6b3dd26474872ae522ea73
predictions/validation_nst/step_45000.md36.8 KBcce821b007176f3db808ad963c7ee9d409535a8df9d53ed96377a793950f53cf
predictions/validation_nst/step_49999.md36.8 KB02ecae94a4d03ecc11e71125f3db46b8e209c4a59239e9844a52be560d51d9d6
predictions/validation_nst/step_5000.md36.8 KBd6d93a7c3248471bdc7023dbe50cf12fda1019cc8763155713e15fdb4b7fa42f
preprocessor_config.json339 Ba6a76d28c93edb273669eb9e0b0636a2bddbb1272c3261e47b7ca6dfdbac1b8d
pytorch_model.bin967 MB6f4bb34d550b48b61c6cbba2786612cd844a621cfe1b152c3e60b79798299a90
runs/Jan07_21-39-59_t1v-n-3c897cb1-w-4/events.out.tfevents.1704663599.t1v-n-3c897cb1-w-4.18033.0.v283.1 MB243fee62226d11ea25c3b5c57e3719c1da36e59f37f7b6081aab1ac7807f2ff1
special_tokens_map.json2.19 KB4679897a50cc1aea98b7d63b8c928b407f252683d3248add11d091e66cf0d5f1
stats.md6.39 KBe84a1ad3caaa21e182da801a0b76d8a284580aa0aa56b99fa23b278154747738
test_results.json367 B13a59a3660e5e5b2b63b34230269de7b735c1f13f8bba26958450accf6e898b3
tokenizer.json2.48 MB87b38f7a654dbbda293bcdda048d2fb18af241fdd41c62496f8e732209610ec1
tokenizer_config.json283 KB348e80c42b59d4e005fdc7a68ad0244ed339e30eaaabcf805e8e28ef73e7d1e8
training_state.bin6.33 KBef6f341ce686fb5a2c9064b5a0b9e2e5ad84961eff2b46f1773a6af52b6bf23c
training_tokenizer-merges.txt494 KB78f27f801feb4283ae969d4cadacb28fc051b655647402b1a252c7079ea11c46
training_tokenizer-vocab.json836 KB8f680bba319e01a653d2e8a5dbc17a9157179e0576e6ce74ce0c06356c6e24f9
update_template.py822 Bd32f76dfc7d3feaece60a64de172710e78c9b3823be2abd31edb020d172379a2
vocab.json836 KB8f680bba319e01a653d2e8a5dbc17a9157179e0576e6ce74ce0c06356c6e24f9
vocabulary.json1.07 MB5ad28279db5e546349708b9a74736e2c018737ac5a600f1048f1f26c99b85b47
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
e9bb5cb83c pinned now2026-11-15 04:57 UTC67 files · 7.44 GB

Use it

$ fw get NbAiLab/nb-whisper-small
# manifest sha256 eb86da2fccea… · 7.44 GB · 67 files
$ fw verify ./nb-whisper-small NbAiLab/nb-whisper-small
fw.pyChecks the signature and every sha256, tries each source in order, resumes.
$ python3 fw.py get https://freeweights.allternit.com/manifests/NbAiLab/nb-whisper-small.json --dir ./nb-whisper-small $ python3 fw.py verify ./nb-whisper-small ./NbAiLab__nb-whisper-small.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download NbAiLab/nb-whisper-small --revision e9bb5cb83cb74c96239fd506163aa97cff2fce4c --local-dir ./nb-whisper-small
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="NbAiLab/nb-whisper-small", revision="e9bb5cb83cb74c96239fd506163aa97cff2fce4c") print(asr("audio.wav")["text"])

License

Name
Apache License 2.0
Id
Apache-2.0
Class
Permissive
Redistribution
yes
Listing
Hosted (signed)
Decided
License as declared by the publisher. No person read it. 2026-11-15
Text in
README.md
Text sha256
c3051e53f686ac892a144b808817b526c4b2f58c6c9c9c89bc9cb0a35687c541
Terms gate
No extra terms beyond the license.

Read the license text

Licenses are checked against the license table. A custom license passes only after a person reads it.

Provenance

From: NbAiLab <huggingface.co/NbAiLab>Newsgroups: alt.freeweights.speechSubject: nb-whisper-smallDate: 2026-11-15Commit: e9bb5cbSigned: 2DC28CC7B26A283B ✓
Upstream
NbAiLab/nb-whisper-small
Pinned commit
e9bb5cb83cb74c96239fd506163aa97cff2fce4c
Manifest
nb-whisper-small.json · .minisig
Manifest sha256
eb86da2fccea2068cde94fa7acc3af39ac204a19b5b5bdb5000b5de4bfeade63
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-15 04:57 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/NbAiLab/nb-whisper-small.json $ curl -O https://freeweights.allternit.com/manifests/NbAiLab/nb-whisper-small.json.minisig $ minisign -Vm nb-whisper-small.json -P RWQ7KGqyx4zCLXtUFOqvfv8L3g+8fpKJ1FsuxPyOYMF+4KufbUxKq1Oq $ shasum -a 256 <file> # compare with the Files tab

A manifest whose signature fails must be rejected. A file whose size or sha256 does not match must be discarded. Verify a download

Model tree

Parent

openai/whisper-small · this model is a quantization of it

1 model in the catalog name this one as their parent.

Quantizations
1
Get it
Download
$ HF_ENDPOINT=https://freeweights.allternit.com hf download NbAiLab/nb-whisper-small
Open in Freeweights Studio

Pull, verify and run it in the Allternit app on Desktop, web or phone.

Signed manifest
minisign, key 2DC28CC7B26A283B. nb-whisper-small.json. Provenance. Takedown history: none.

Variants

1 quantized or adapter build of nb-whisper-small. Each has its own license check and page.

From: MIT <huggingface.co/MIT>Subject: ast-finetuned-audioset-10-10-0.4593
From: onnx-community <huggingface.co/onnx-community>Subject: ast-finetuned-audioset-10-10-0.4593-ONNX
From: Edge0 <huggingface.co/Edge0>Subject: Audio8-TTS-Preview-0.6b
From: Edge0 <huggingface.co/Edge0>Subject: Audio8-TTS-Realistic-Air
From: facebook <huggingface.co/facebook>Subject: audiobox-aesthetics
From: mlx-community <huggingface.co/mlx-community>Subject: chatterbox-4bit