# Whisper fine-tuning

KinyaWhisper is a fine-tuned Kinyarwanda automatic speech recognition (ASR) system based on OpenAI's Whisper model, specifically designed for low-resource indigenous languages.

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%.

Fine-tuned the openai/whisper-large-v3-turbo based on the Indian English accent dataset, which is more suitable for speech recognition of Indian English accents.

This model is a fine-tuned Arabic speech recognition model based on openai/whisper-base on the quran-ayat-speech-to-text dataset, specializing in the task of converting Quranic verses from speech to text.

A speech recognition model fine-tuned on the Polish Common Voice 17.0 dataset based on OpenAI Whisper-base

Whisper-medium model optimized for Vietnamese speech recognition tasks, fine-tuned on 1308 hours of Vietnamese data

A Cantonese automatic speech recognition model fine-tuned on Whisper v3, trained on the Common Voice 17 dataset

A fine-tuned version of OpenAI's Whisper model, specifically designed for automatic speech recognition tasks in the low-resource Ghanaian language Akan

A speech recognition model fine-tuned based on openai/whisper-small, specifically optimized for Khmer transcription accuracy

This model is an automatic speech recognition (ASR) model fine-tuned on Burmese speech datasets based on openai/whisper-tiny, supporting Burmese speech-to-text tasks.

This model is an automatic speech recognition model fine-tuned on the Burmese speech dataset based on openai/whisper-large-v3, specifically designed for Burmese speech transcription.

Monsoon-Whisper-Medium-GigaSpeech2 is a Thai automatic speech recognition (ASR) model, based on Whisper-Medium and fine-tuned on the GigaSpeech2 dataset, suitable for speech recognition in real-world scenarios.

Kyrgyz Whisper ASR is a customized automatic speech recognition solution specifically designed for the Kyrgyz language, fine-tuned based on the pre-trained Whisper model.

A Whisper-large-v3 fine-tuned model for Taiwanese Hakka speech recognition, supporting multiple Hakka dialects

A language identification model fine-tuned based on the Whisper Medium model, specifically designed for language classification tasks on the FLEURS dataset

A Sinhala speech recognition model fine-tuned based on openai/whisper-small, supporting conversion of Sinhala speech to text.

Kyrgyz automatic speech recognition (ASR) model based on the Whisper architecture, developed with support from the National Commission on Language and Language Policy under the President of the Kyrgyz Republic

Vietnamese automatic speech recognition (ASR) model fine-tuned based on OpenAI Whisper-tiny architecture, demonstrating excellent performance on multiple Vietnamese datasets

PhoWhisper is a series of models designed specifically for Vietnamese automatic speech recognition (ASR). It achieves high robustness by fine-tuning the Whisper model on an 844-hour Vietnamese accent dataset.

PhoWhisper is a system specifically designed for Vietnamese automatic speech recognition, fine-tuned based on the Whisper model, supporting various Vietnamese accents.

PhoWhisper is a system specifically designed for Vietnamese automatic speech recognition, fine-tuned based on the Whisper model, supporting various Vietnamese accents.

The Whisper (small) model fine-tuned by the Hezar team based on the Persian part of the Common Voice dataset, which can be used for automatic speech recognition tasks.

A speech recognition model fine-tuned on the Common Voice 13.0 Spanish dataset based on OpenAI Whisper-large-v2

A fine-tuned whisper medium model based on the CommonVoice-14.0 Persian dataset for Persian automatic speech recognition tasks.

This is a Bengali automatic speech recognition model based on the Whisper small architecture, fine-tuned on approximately 400 hours of Mozilla Common Voice dataset with a word error rate of 4.58%

An African language speech recognition model fine-tuned from Whisper-large-v2, trained on the afrispeech-200 dataset with a word error rate (WER) of 14.81

An Arabic speech recognition model fine-tuned based on openai/whisper-medium, supporting streaming processing

Spanish speech recognition model fine-tuned based on openai/whisper-large-v2, achieving 8.55% WER on Common Voice 11.0 Spanish test set

This model is a fine-tuned speech recognition model based on OpenAI's Whisper Large V2 on the Kazakh Common Voice 11.0 dataset

A Portuguese speech recognition model fine-tuned on the common_voice_11_0 dataset based on openai/whisper-medium, with a word error rate of 6.5987