Hugging Face's logo

aisak-ai
/
stt

Automatic Speech Recognition
Transformers
Safetensors
whisper
audio
speech-to-text
Inference Endpoints
Model card Files Community
stt / README.md
mandelakori's picture
mandelakori
Update README.md
3eb569c verified
preview code
|
raw
history blame
4.3 kB
metadata
language:
  - en
  - zh
  - de
  - es
  - ru
  - ko
  - fr
  - ja
  - pt
  - tr
  - pl
  - ca
  - nl
  - ar
  - sv
  - it
  - id
  - hi
  - fi
  - vi
  - he
  - uk
  - el
  - ms
  - cs
  - ro
  - da
  - hu
  - ta
  - 'no'
  - th
  - ur
  - hr
  - bg
  - lt
  - la
  - mi
  - ml
  - cy
  - sk
  - te
  - fa
  - lv
  - bn
  - sr
  - az
  - sl
  - kn
  - et
  - mk
  - br
  - eu
  - is
  - hy
  - ne
  - mn
  - bs
  - kk
  - sq
  - sw
  - gl
  - mr
  - pa
  - si
  - km
  - sn
  - yo
  - so
  - af
  - oc
  - ka
  - be
  - tg
  - sd
  - gu
  - am
  - yi
  - lo
  - uz
  - fo
  - ht
  - ps
  - tk
  - nn
  - mt
  - sa
  - lb
  - my
  - bo
  - tl
  - mg
  - as
  - tt
  - haw
  - ln
  - ha
  - ba
  - jw
  - su
tags:
  - audio
  - automatic-speech-recognition
  - speech-to-text
pipeline_tag: automatic-speech-recognition
license: other
license_name: all-rights-reserved

AISAK-Listen

Overview:

AISAK, short for Artificially Intelligent Swiss Army Knife, is a general-purpose AI system comprising various models designed for different tasks. Developed by the AISAK team, one of the models within AISAK is a state-of-the-art automatic speech recognition (ASR) model. This model, named AISAK-Listen, is fine-tuned on extensive datasets to excel in converting spoken language into written text.

Model Information:

  • Model Name: AISAK-Listen
  • Version: 1.0
  • Model Architecture: Seq2seq
  • Specialization: AISAK-Listen is a dedicated ASR model within the AISAK system, built off the impressive https://huggingface.co/openai/whisper-tiny model architecture. It has been fine-tuned to optimize performance for quick speech recognition tasks.

Intended Use:

AISAK-Listen, as part of AISAK, is developed to provide reliable and high-quality speech-to-text conversion capabilities. It is intended to be a versatile tool for various applications such as transcription services, voice assistants, voice-controlled systems, and more. AISAK-Listen excels in accurately transcribing quick speech with minimal delay, making it suitable for real-time speech recognition requirements.

Performance:

AISAK-Listen has undergone extensive testing to ensure its performance meets demanding standards. It consistently achieves impressive accuracy rates in converting spoken language to written text, outperforming other ASR models in terms of speed and efficiency. The model's performance has been evaluated on diverse speech datasets to ensure its generalization across different speakers and speech patterns.

Ethical Considerations:

  • Bias Mitigation: AISAK-Listen undergoes training processes that aim to minimize bias. However, it is important to note that biases may still be present in the transcriptions generated by the model.
  • Fair Use: Users are advised to exercise caution when utilizing AISAK-Listen in sensitive or critical contexts. The generated transcriptions should be reviewed and verified to ensure their accuracy and fairness.

Limitations:

  • AISAK-Listen's performance is optimized for quick speech recognition and may not be as effective for specialized speech styles or accents.
  • The model's accuracy may vary when exposed to speech data that significantly differs from the quick speech it was trained on.

Deployment:

Inferencing for AISAK-Listen will be handled as part of the full deployment of the AISAK system in the future. The process is lengthy and intensive in many areas, emphasizing the goal of achieving the optimal system rather than the quickest. However, work is being done as fast as humanly possible. Updates will be provided as frequently as possible.

Caveats:

  • It is recommended to review and validate the transcriptions generated by AISAK-Listen, particularly in critical or high-stakes situations where accuracy is crucial.

Contact Information: For any inquiries or communication regarding AISAK, please contact me at mandelakorilogan@gmail.com.

© 2024 Mandela Logan. All rights reserved.

No part of this model may be reproduced, distributed, or transmitted in any form or by any means, including photocopying, recording, or other electronic or mechanical methods, without the prior written permission of the copyright holder. Users are expressly prohibited from creating replications or spaces derived from this model, whether in whole or in part, without the explicit authorization of the copyright holder. Unauthorized use or reproduction of this model is strictly prohibited by copyright law.