updated template

README.md

@@ -9,7 +9,7 @@ datasets:
 - NbAiLab/ncc_speech
 - NbAiLab/NST
 - NbAiLab/NPSC
-base_model: openai/whisper-tiny
+base_model: openai/whisper-small
 tags:
 - audio
 - asr
@@ -28,35 +28,32 @@ widget:
 ---
 
 
-# NB-Whisper Tiny (Release Candidate)
+# NB-Whisper Small
 
-**IMPORTANT:** These models are currently Release Candidates. We are in the final stages of testing. If everything proceeds smoothly, we plan to officially release the models later this month.
-
-Introducing the **_Norwegian NB-Whisper Tiny 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](https://arxiv.org/abs/2212.04356). 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.
+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](https://arxiv.org/abs/2212.04356). 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 Size | Parameters | Model |
 |------------|------------|------------|
-| Tiny       | 39M        | [NB-Whisper Tiny](https://huggingface.co/NbAiLabBeta/nb-whisper-tiny) |
-| Base       | 74M        | [NB-Whisper Base](https://huggingface.co/NbAiLabBeta/nb-whisper-base) |
-| Small      | 244M       | [NB-Whisper Small](https://huggingface.co/NbAiLabBeta/nb-whisper-small) |
-| Medium     | 769M       | [NB-Whisper Medium](https://huggingface.co/NbAiLabBeta/nb-whisper-medium) |
-| Large      | 1550M      | [NB-Whisper Large](https://huggingface.co/NbAiLabBeta/nb-whisper-large) |
+| Tiny       | 39M        | [NB-Whisper Tiny](https://huggingface.co/NbAiLab/nb-whisper-tiny) |
+| Base       | 74M        | [NB-Whisper Base](https://huggingface.co/NbAiLab/nb-whisper-base) |
+| Small      | 244M       | [NB-Whisper Small](https://huggingface.co/NbAiLab/nb-whisper-small) |
+| Medium     | 769M       | [NB-Whisper Medium](https://huggingface.co/NbAiLab/nb-whisper-medium) |
+| Large      | 1550M      | [NB-Whisper Large](https://huggingface.co/NbAiLab/nb-whisper-large) |
 
 
 
-### Specialised Models
+### 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.
-- **Semantic version**: This variant focuses less on verbatim accuracy but captures the essence of content, ideal for meeting minutes and subtitling.
 
 
-| Model Size | Parameters | Verbatim version | Semantic version |
-|------------|------------|------------|------------------|
-| Tiny       | 39M        | [Tiny - verbatim](https://huggingface.co/NbAiLabBeta/nb-whisper-tiny-verbatim) | [Tiny - semantic](https://huggingface.co/NbAiLabBeta/nb-whisper-tiny-semantic) |
-| Base       | 74M        | [Base - verbatim](https://huggingface.co/NbAiLabBeta/nb-whisper-base-verbatim) | [Base - semantic](https://huggingface.co/NbAiLabBeta/nb-whisper-base-semantic) |
-| Small      | 244M       | [Small - verbatim](https://huggingface.co/NbAiLabBeta/nb-whisper-small-verbatim) | [Small - semantic](https://huggingface.co/NbAiLabBeta/nb-whisper-small-semantic) |
-| Medium     | 769M       | [Medium - verbatim](https://huggingface.co/NbAiLabBeta/nb-whisper-medium-verbatim) | [Medium - semantic](https://huggingface.co/NbAiLabBeta/nb-whisper-medium-semantic) |
-| Large      | 1550M      | [Large - verbatim](https://huggingface.co/NbAiLabBeta/nb-whisper-large-verbatim) | [Large - semantic](https://huggingface.co/NbAiLabBeta/nb-whisper-large-semantic) |
+| Model Size | Parameters | Semantic version |
+|------------|------------|------------------|
+| Tiny       | 39M        | [Tiny - semantic](https://huggingface.co/NbAiLab/nb-whisper-tiny-semantic) |
+| Base       | 74M        | [Base - semantic](https://huggingface.co/NbAiLab/nb-whisper-base-semantic) |
+| Small      | 244M       | [Small - semantic](https://huggingface.co/NbAiLab/nb-whisper-small-semantic) |
+| Medium     | 769M       | [Medium - semantic](https://huggingface.co/NbAiLab/nb-whisper-medium-semantic) |
+| Large      | 1550M      | [Large - semantic](https://huggingface.co/NbAiLab/nb-whisper-large-semantic) |
 
 
 ### Model Description
@@ -66,7 +63,7 @@ While the main models are suitable for most transcription task, we demonstrate h
 - **Model type:** `whisper`
 - **Language(s) (NLP):** Norwegian, Norwegian Bokmål, Norwegian Nynorsk, English
 - **License:** [Apache 2.0](https://www.apache.org/licenses/LICENSE-2.0)
-- **Trained from model:** [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny)
+- **Trained from model:** [openai/whisper-small](https://huggingface.co/openai/whisper-small)
 - **Code Repository:** https://github.com/NbAiLab/nb-whisper/
 - **Paper:** _Coming soon_
 - **Demo:** _See Spaces on this page_
@@ -75,7 +72,7 @@ While the main models are suitable for most transcription task, we demonstrate h
 ## 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](https://huggingface.co/NbAiLabBeta/).
+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](https://huggingface.co/NbAiLab/).
 
 ### 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](https://www.python.org/downloads/) installed on your machine. For practical demonstrations, refer to examples using this [sample mp3 file](https://github.com/NbAiLab/nb-whisper/raw/main/audio/king.mp3).
@@ -94,7 +91,7 @@ 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-tiny")
+asr = pipeline("automatic-speech-recognition", "NbAiLabBeta/nb-whisper-small")
 
 #transcribe
 asr("king.mp3", generate_kwargs={'task': 'transcribe', 'language': 'no'})
@@ -223,14 +220,14 @@ $ 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/NbAiLabBeta/nb-whisper-tiny/resolve/main/ggml-model.bin -O models/nb-tiny-ggml-model.bin
-wget -N https://huggingface.co/NbAiLabBeta/nb-whisper-tiny/resolve/main/ggml-model-q5_0.bin -O models/nb-tiny-ggml-model-q5_0.bin
+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-tiny-ggml-model.bin king.wav
+$ ./main -l no -m models/nb-small-ggml-model.bin king.wav
 
 # Or the quantized version
-$ ./main -l no -m models/nb-tiny-ggml-model-q5_0.bin king.wav
+$ ./main -l no -m models/nb-small-ggml-model-q5_0.bin king.wav
 ```
 
 ### WhisperX and Speaker Diarization
@@ -250,7 +247,7 @@ wget -N https://github.com/NbAiLab/nb-whisper/raw/main/audio/knuthamsun.mp3
 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-tiny --language no --diarize
+whisperx knuthamsun.mp3 --model NbAiLabBeta/nb-whisper-small --language no --diarize
 
 ```
 
@@ -282,7 +279,7 @@ Using these models without adequate risk assessment and mitigation could be cons
 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](https://github.com/NbAiLab/nb-whisper/).
 
 ## Citation & Contributors
-The NB-Whisper Tiny model is a product of the NoSTram project led by Per Egil Kummervold ([@pere](https://huggingface.co/pere)) at the National Library of Norway. Key contributors include Javier de la Rosa ([@versae](https://huggingface.co/versae)), Freddy Wetjen ([@freddyw](https://huggingface.co/freddyw)), and Rolv-Arild Braaten ([@Rolv-Arild](https://huggingface.co/Rolv-Arild)). NB AI-Lab, under the direction of Svein Arne Brygfjeld ([@Brygfjeld](https://huggingface.co/Brygfjeld)), supported the project's successful completion. A detailed paper on our process and findings is forthcoming.
+The NB-Whisper Small model is a product of the NoSTram project led by Per Egil Kummervold ([@pere](https://huggingface.co/pere)) at the National Library of Norway. Key contributors include Javier de la Rosa ([@versae](https://huggingface.co/versae)), Freddy Wetjen ([@freddyw](https://huggingface.co/freddyw)), and Rolv-Arild Braaten ([@Rolv-Arild](https://huggingface.co/Rolv-Arild)). NB AI-Lab, under the direction of Svein Arne Brygfjeld ([@Brygfjeld](https://huggingface.co/Brygfjeld)), supported the project's successful completion. A detailed paper on our process and findings is forthcoming.
 
 ## Disclaimer