# Low word error rate

An automatic speech recognition model fine-tuned on Vietnamese speech data based on openai/whisper-small, improving Vietnamese transcription accuracy and robustness

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%

Persian automatic speech recognition model optimized based on OpenAI Whisper-large-v3-turbo, supporting medical field applications

A speech recognition model fine-tuned on 100 hours of Vietnamese speech data based on openai/whisper-base model, improving Vietnamese transcription accuracy

A Persian automatic speech recognition model fine-tuned based on Whisper Large v3, trained using the Common Voice 17 dataset, significantly improving Persian recognition accuracy.

A Hindi speech recognition model fine-tuned based on OpenAI's Whisper-Large-V3, trained on approximately 718 hours of transcribed Hindi speech data

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.

An automatic speech recognition model fine-tuned on the Hungarian Common Voice dataset based on facebook/wav2vec2-large-xlsr-53

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.

Uzbek automatic speech recognition model fine-tuned from OpenAI Whisper Medium

Whisper model released by the Swedish National Library, optimized for Swedish, trained on 50,000+ hours of Swedish speech data, outperforming the original OpenAI version

A Whisper model trained on over 50,000 hours of Swedish speech data released by the National Library of Sweden, excelling in Swedish speech recognition tasks

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.

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 Korean automatic speech recognition model optimized based on Whisper Large v3 Turbo, providing high-accuracy transcription with timestamps

A large-scale Vietnamese automatic speech recognition model based on the ChunkFormer architecture, fine-tuned on approximately 3000 hours of publicly available Vietnamese speech data, with excellent performance.

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

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.

A Tajik automatic speech recognition model fine-tuned from OpenAI Whisper-small, trained on Google Fleurs dataset with a word error rate of 24.26%.

A Quran speech recognition model fine-tuned based on OpenAI Whisper-small, specifically designed for Arabic Quran audio

German speech recognition model optimized based on Whisper Large v3 Turbo, fine-tuned on a 13-hour curated dataset, significantly improving German recognition accuracy

Uzbek speech recognition model fine-tuned on Whisper Base, trained on the Common Voice dataset

An automatic speech recognition (ASR) model fine-tuned on Turkish Khan Academy dataset based on OpenAI Whisper-large-v3-turbo

German speech recognition model optimized based on Whisper architecture, with 39 million parameters, supporting efficient German speech transcription

A Latvian automatic speech recognition model fine-tuned based on whisper-large-v3, trained by AiLab.lv, supporting Latvian speech-to-text tasks.

Hungarian speech recognition model fine-tuned based on OpenAI Whisper-base, trained on 1200 hours of Hungarian data, outperforming similar models

A Turkish speech recognition model fine-tuned on the Common Voice 17.0 dataset based on openai/whisper-large-v3-turbo

Spanish speech recognition model fine-tuned based on Whisper-large-v3-turbo, achieving a word error rate reduction to 5.34% on the Common Voice 17.0 Spanish dataset

Based on the transformers library, this is a fine-tuned version of openai/whisper-large-v3-turbo on the common_voice_11_0 dataset, optimized specifically for Arabic speech recognition.

A Whisper small speech recognition model fine-tuned on the Common Voice 17.0 Marathi dataset, based on simran14/mr-model-h

A Kurdish Sorani dialect speech recognition model fine-tuned based on openai/whisper-small

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.

This model is an automatic speech recognition (ASR) model fine-tuned on the Azerbaijani Common Voice 17.0 dataset based on OpenAI's Whisper Large v3, achieving a word error rate (WER) of 1.195%.

A Russian speech recognition model fine-tuned based on OpenAI Whisper-large-v3, optimized for Russian recognition performance

A speech recognition model fine-tuned on the Common Voice 17.0 Turkish dataset based on OpenAI Whisper-large-v3

A Ge'ez (Ethiopian) text processing model based on the T5 architecture, supporting text generation and transformation tasks

Distil-Whisper is a distilled version of the Whisper model, optimized for long-form transcription, offering faster inference speed and improved word error rate (WER) performance.

A speech recognition model fine-tuned on Dutch datasets based on OpenAI Whisper Large V2, with a word error rate of 10.14%

A speech recognition model fine-tuned on the Common Voice 16.0 dataset based on OpenAI Whisper Large V3

A fine-tuned Basque automatic speech recognition model based on facebook/wav2vec2-xls-r-300m, achieving a 3.67% word error rate on the Basque Parliament dataset