Update license, paper title, and code repository link

README.md

@@ -1,14 +1,17 @@
 ---
-license: other 
 language:
-- uk 
+- uk
 library_name: transformers
+license: apache-2.0
 pipeline_tag: automatic-speech-recognition
-arxiv: https://arxiv.org/abs/2509.02523 
+arxiv: https://arxiv.org/abs/2509.02523
 ---
+
 # Moonshine
 
-[[Paper]](https://arxiv.org/abs/2509.02523) [[Installation]](https://github.com/usefulsensors/moonshine/blob/main/README.md)
+## Flavors of Moonshine: Tiny Specialized ASR Models for Edge Devices
+
+[[Paper]](https://arxiv.org/abs/2509.02523) [[Code]](https://github.com/usefulsensors/moonshine)
 
 This is the model card for running the automatic speech recognition (ASR) models (Moonshine models) trained and released by Moonshine AI (f.k.a Useful Sensors.)
 
@@ -56,13 +59,13 @@ print(processor.decode(generated_ids[0], skip_special_tokens=True))
 
 ## Model Details
 
-This Moonshine model is trained for the speech recognition task, capable of transcribing Ukranian speech audio into Ukrainian text.  Moonshine AI developed the models to support their business direction of developing real time speech transcription products based on low cost hardware. The following table shows comparisons of common ASR evaluations sets. For more information about evaluation, please refer to the paper.
+This Moonshine model is trained for the speech recognition task, capable of transcribing Ukranian speech audio into Ukrainian text. Moonshine AI developed the models to support their business direction of developing real time speech transcription products based on low cost hardware. The following table shows comparisons of common ASR evaluations sets. For more information about evaluation, please refer to the paper.
 
 | Size | Parameters | Fleurs (WER) ↓ | Common Voice 17 (WER) ↓ |
 |:----:|:----------:|:------------------:|:------------------:|
-| whisper tiny | 39 M       |      63.83             | 67.07                    |
-| whisper medium | 769 M       |  11.62                 | 20.9                 |
-| moonshine tiny | 27 M       | 18.25                  | 26.11                  |
+| whisper tiny | 39 M | 63.83 | 67.07 |
+| whisper medium | 769 M | 11.62 | 20.9 |
+| moonshine tiny | 27 M | 18.25 | 26.11 |
 
 ### Release date
 
@@ -92,7 +95,7 @@ Our evaluations show that, the models exhibit greater accuracy on standard datas
 
 However, like any machine learning model, the predictions may include texts that are not actually spoken in the audio input (i.e. hallucination). We hypothesize that this happens because, given their general knowledge of language, the models combine trying to predict the next word in audio with trying to transcribe the audio itself.
 
-In addition, the sequence-to-sequence architecture of the model makes it prone to generating repetitive texts, which can be mitigated to some degree by beam search and temperature scheduling but not perfectly. It is likely that this behavior and hallucinations may be worse for short audio segments, or segments where parts of words are cut off at the beginning or the end of the segment.
+In addition, the sequence-to-sequence architecture of the model makes it prone to generating repetitive texts, which can be mitigated to some degree by beam search and temperature scheduling but not perfectly. It is likely that this behavior and hallucinations may be worse for short audio segments, or segments where parts of words are cut off at the beginning or at the end of the segment.
 
 ## Broader Implications
 
@@ -113,4 +116,4 @@ If you benefit from our work, please cite us:
       primaryClass={cs.CL},
       url={https://arxiv.org/abs/2509.02523}, 
 }
-```
+```