This is an English automatic speech recognition model developed by Applied Brain Research (ABR) based on the state space model (SSM). It has approximately 19 million parameters and can efficiently and accurately transcribe English speech into text. The model performs excellently on multiple benchmark datasets, with an average word error rate of only 10.61%. It supports real-time speech recognition and can run on low-cost hardware.

Audio ProcessingTransformersEnglish

This model is an automatic speech recognition model fine-tuned for Swahili based on the OpenAI Whisper-small model. It was trained on the Swahili part of the FLEURS-SLU dataset, significantly improving the transcription accuracy of Swahili. The word error rate was reduced by 68% compared to the base model.

Audio ProcessingTransformersOther

This is a Bambara speech recognition model fine-tuned based on the OpenAI Whisper Small model. It was trained on 24,738 Bambara audio samples and can accurately transcribe Bambara speech into text, with a character error rate as low as 21.69%.

Audio ProcessingSafetensorsOther

This model is an automatic speech recognition model fine-tuned on Latin based on OpenAI Whisper-small. It is trained using 67 hours of Latin audio data, with a character error rate (CER) of 20. It supports the task of converting Latin speech to text.

Audio ProcessingSafetensorsOther

An aviation traffic control speech recognition model fine-tuned based on the OpenAI Whisper Large v3 model, specifically optimized for ATC communication scenarios. It achieved a word error rate of 6.5% on the test set, significantly improving the accuracy of aviation communication transcription.

Audio ProcessingTransformersEnglish

This model is an automatic speech recognition model fine-tuned on the Egyptian Arabic dialect dataset (Egyptian-ASR-MGB-3) using the LoRA method, based on OpenAI's Whisper Large V3 model. It is specifically optimized for the recognition ability of the Egyptian Arabic dialect, significantly improving the word error rate (WER) performance on this dialect.

Audio ProcessingPeftArabic

This is an automatic speech recognition model fine-tuned based on the wav2vec2-large-xlsr-53 architecture, specifically optimized for Egyptian Arabic, Modern Standard Arabic, and Gulf/Levantine Arabic. The model is trained on multiple Arabic speech datasets and achieves a word error rate of 27.20% on the Common Voice 17.0 Arabic test set, outperforming many similar models.

Audio ProcessingTransformersMultiple Languages

This is an automatic speech recognition model fine-tuned on approximately 1000 hours of Kazakh speech data based on the Whisper large-v3-turbo model, with a character error rate of 9.16% on the test set.

Audio ProcessingTransformersOther

This model is a speech recognition model fine-tuned on the LibriSpeech dataset based on facebook/wav2vec2-base, achieving a word error rate of 0.3174 on the evaluation set.

Audio ProcessingTransformers

A Hausa speech recognition model fine-tuned from facebook/w2v-bert-2.0, trained on 500 hours of Hausa data with a word error rate of 7.47%

Audio ProcessingTransformers

This model is a speech recognition model fine-tuned on the Tamil Common Voice 17.0 dataset based on OpenAI's Whisper Small, with a Word Error Rate (WER) of 43.23%.

Audio ProcessingTransformersOther

An Indian English accent speech recognition model fine-tuned based on OpenAI Whisper-large-v3-turbo, achieving a 7.99% word error rate on Indian English accent datasets

Audio ProcessingTransformersEnglish

This is a Whisper-small speech recognition model fine-tuned on French datasets, reducing the word error rate by 6.793 percentage points compared to the baseline model.

Audio ProcessingTransformersFrench

Whisper-large-v3-turbo fine-tuned model for Indian English accent speech recognition, with a word error rate of 4.39%

Audio ProcessingTransformersEnglish

A Danish speech recognition model trained on Whisper Large v3, fine-tuned on the CoRaL dataset, with excellent word error rate and character error rate performance.

Audio ProcessingTransformersOther

A Whisper model released by the National Library of Sweden, optimized for Swedish speech recognition, significantly reducing the error rate compared to the original OpenAI version.

Audio ProcessingTransformersOther

A Swedish speech recognition model based on the Whisper architecture released by the National Library of Sweden. The training data exceeds 50,000 hours, significantly reducing the word error rate.

Audio ProcessingTransformersOther

KB-Whisper Base is a Swedish speech recognition model released by the National Library of Sweden. Based on OpenAI's Whisper architecture, it is trained on over 50,000 hours of Swedish speech data. Compared with OpenAI's whisper-large-v3 model, it reduces the word error rate (WER) by an average of 47%, significantly improving the accuracy of Swedish speech recognition.

Audio ProcessingTransformersOther

Amharic speech recognition model fine-tuned from openai/whisper-small, achieving a word error rate of 2.0538% on the evaluation set

Audio ProcessingTransformers

This model is a Russian automatic speech recognition (ASR) model fine-tuned on the common_voice_17_0 dataset based on facebook/wav2vec2-xls-r-300m, with a word error rate (WER) of 0.195.

Audio ProcessingTransformers