# Multi-dialect support

Roest Wav2vec2 1B V2
Openrail
This is Denmark's most advanced speech recognition model, trained by Alvenir as part of the CoRal project, based on the CoRal-v2 dataset, covering various Danish dialects.
Speech Recognition Other
R
CoRal-project
91
1
Roest Wav2vec2 315m V2
Openrail
Denmark's state-of-the-art speech recognition model trained by Alvenir, based on the CoRal-v2 dataset, supporting multiple Danish dialects
Speech Recognition Safetensors Other
R
CoRal-project
238
2
Nllb1.3 Smugri4 V0.01
This is a version of the NLLB-1.3b model fine-tuned with parallel data for 29 Finno-Ugric languages, supporting the generation of multiple dialects/variants.
Machine Translation Transformers Supports Multiple Languages
N
tartuNLP
39
2
Wav2vec LnNor IPA Ft
A phoneme recognition model fine-tuned based on wav2vec2-base, supporting English speech to International Phonetic Alphabet (IPA) conversion
Speech Recognition English
W
MultiBridge
16
1
Whisper Uz
Apache-2.0
Uzbek automatic speech recognition model fine-tuned from OpenAI Whisper Medium
Speech Recognition Transformers Other
W
mustafoyev202
110
1
Arabic Retrieval V1.0
Apache-2.0
A high-performance Arabic information retrieval model built on the sentence-transformers framework, optimized for the richness and complexity of the Arabic language.
Text Embedding Arabic
A
omarelshehy
366
3
Nb Whisper Large Distil Turbo Beta
Apache-2.0
A lightweight and accelerated version of the Norwegian automatic speech recognition model developed by the National Library of Norway, reducing parameter count through distillation while maintaining transcription quality.
Speech Recognition Transformers Supports Multiple Languages
N
NbAiLab
478
1
Whisper Large V3 Turbo Cantonese Yue English
MIT
A Cantonese and English mixed speech recognition model optimized based on the Whisper architecture, supporting high-precision bilingual transcription
Speech Recognition Transformers
W
JackyHoCL
73
4
Whisper Tiny Myanmar
Apache-2.0
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.
Speech Recognition Transformers Other
W
chuuhtetnaing
84
1
Arabic Alphabet Speech Classification
This is a transformers model for Arabic alphabet speech classification, capable of recognizing and classifying the pronunciation of Arabic letters.
Audio Classification Transformers
A
HamzaSidhu786
60
1
Nepali Male V1
Apache-2.0
Nepali male voice synthesis model based on VITS architecture, supporting high-quality text-to-speech functionality
Speech Synthesis Transformers Other
N
tuskbyte
78
0
Speech Accent Pt Br Classifier
A speech-based accent classifier for distinguishing Brazilian Portuguese from other accents.
Audio Classification Transformers Supports Multiple Languages
S
rmayormartins
24
2
Mms Tts Nova Train
CC
This is a Shan language text-to-speech (TTS) model designed to convert Shan text into natural speech.
Speech Synthesis Transformers Other
M
NorHsangPha
28
0
Adabtranslate Darija
Apache-2.0
A translation model for Darija (Moroccan Arabic) to Modern Standard Arabic (MSA), trained on 26,000 manually annotated and GPT-4 enhanced text pairs
Machine Translation Transformers
A
itsmeussa
35
8
Nb Whisper Base
Apache-2.0
An automatic speech recognition model developed by the National Library of Norway, based on the OpenAI Whisper architecture, supporting transcription in Norwegian and English.
Speech Recognition Transformers
N
NbAiLab
1,629
2
Nb Whisper Large
Apache-2.0
An automatic Norwegian speech recognition model launched by the National Library of Norway, developed based on OpenAI's Whisper architecture, supporting multiple Norwegian dialects and English.
Speech Recognition Transformers Supports Multiple Languages
N
NbAiLab
5,214
26
Arabic Morocco Speech To Text
Apache-2.0
Arabic speech recognition model based on Whisper-large-v3, optimized for Moroccan accent
Speech Recognition Transformers Arabic
A
smerchi
194
10
Nb Whisper Large Verbatim
Apache-2.0
Norwegian automatic speech recognition model developed based on OpenAI Whisper, with additional training for lowercase, punctuation-free verbatim transcription
Speech Recognition Supports Multiple Languages
N
NbAiLabBeta
765
2
Nb Whisper Large
Apache-2.0
An automatic speech recognition model developed by the National Library of Norway, based on the Whisper architecture, supporting speech transcription and translation of Norwegian and English.
Speech Recognition Transformers
N
NbAiLabBeta
776
9
Malaysian Whisper Base
Whisper base model fine-tuned on Malaysian datasets, supporting Malay and English speech recognition
Speech Recognition Transformers Supports Multiple Languages
M
mesolitica
143
2
Norbert3 Xs
Apache-2.0
NorBERT 3 xs is a BERT model optimized for Norwegian, the smallest version in the new generation NorBERT language model series with 15M parameters.
Large Language Model Transformers Other
N
ltg
228
4
Norbert3 Base
Apache-2.0
NorBERT 3 is a next-generation Norwegian language model based on the BERT architecture, supporting both Bokmål and Nynorsk written Norwegian.
Large Language Model Transformers Other
N
ltg
345
7
Whisper Large V2 Hausa
Apache-2.0
This model is a fine-tuned version of OpenAI's Whisper Large-V2 for Hausa speech recognition tasks, trained on the Common Voice 11.0 dataset
Speech Recognition Transformers Other
W
DrishtiSharma
44
5
Whisper Small Kab
Apache-2.0
Georgian automatic speech recognition model fine-tuned based on OpenAI Whisper-small
Speech Recognition Transformers Other
W
BlueRaccoon
37
2
Whisper Large V2 Malayalam
Apache-2.0
This is a fine-tuned version of the OpenAI Whisper Large V2 model for Malayalam speech recognition tasks, trained using the Common Voice 11.0 dataset
Speech Recognition Transformers Other
W
DrishtiSharma
23
4
Wav2vec2 Large Xlsr 53 Spanish Ep5 944h
An acoustic model for Spanish automatic speech recognition, fine-tuned for 5 epochs based on facebook/wav2vec2-large-xlsr-53 using approximately 944 hours of Spanish data.
Speech Recognition Transformers Spanish
W
carlosdanielhernandezmena
111
3
Wav2vec2 1b Npsc Nst Bokmaal
Apache-2.0
This model is an automatic speech recognition (ASR) model fine-tuned on the Norwegian Bokmål dialect speech dataset based on facebook/wav2vec2-xls-r-1b
Speech Recognition Transformers
W
NbAiLab
30
0
Opus Mt Tc Big En Pt
This is a neural machine translation model for English to Portuguese (including Brazilian Portuguese), part of the OPUS-MT project.
Machine Translation Transformers Supports Multiple Languages
O
Helsinki-NLP
65.51k
28
Wav2vec2hindiasr
Apache-2.0
Hindi automatic speech recognition (ASR) model based on Wav2Vec2 architecture, fine-tuned on public speech datasets
Speech Recognition Transformers
W
SAGAR4REAL
31
1
Aradia Ctc V1
Automatic speech recognition model trained on a large-scale Arabic speech dataset
Speech Recognition Transformers
A
abdusah
16
0
Wav2vec2 Large Xlsr Hindi
A Hindi automatic speech recognition model fine-tuned on low-resource Indian language datasets based on facebook/wav2vec2-large-xlsr-53
Speech Recognition Transformers Other
W
theainerd
1.6M
7
Wav2vec2 Large Xlsr 53 Breton
Apache-2.0
A Breton fine-tuned speech recognition model based on facebook/wav2vec2-large-xlsr-53
Speech Recognition Other
W
mrm8488
26
0
Wav2vec2 Large Xls R 300m Urdu
Apache-2.0
This is an automatic speech recognition model fine-tuned on the Urdu Common Voice 7 dataset based on facebook/wav2vec2-xls-r-300m.
Speech Recognition Transformers Other
W
infinitejoy
15
0
Wav2vec2 Xls R Hindi
Apache-2.0
This is an automatic speech recognition (ASR) model fine-tuned on the Hindi Common Voice 7.0 dataset based on facebook/wav2vec2-xls-r-300m
Speech Recognition Transformers Other
W
shivam
19
1
Wav2vec2 Large Xlsr Breton
Apache-2.0
A speech recognition model fine-tuned on the Breton Common Voice dataset based on facebook/wav2vec2-large-xlsr-53
Speech Recognition Other
W
cahya
25
1
Xls R Ta
Apache-2.0
Automatic speech recognition model fine-tuned on Tamil dataset based on facebook/wav2vec2-xls-r-300m
Speech Recognition Transformers Other
X
jejomi
22
0
Wav2vec2 Xlsr Tatar
Apache-2.0
This model is an automatic speech recognition model fine-tuned on Tatar language datasets based on facebook/wav2vec2-xls-r-1b, achieving a word error rate (WER) of 16.87% on the Common Voice 8 dataset.
Speech Recognition Transformers Other
W
sammy786
17
1
Wav2vec2 Large Xlsr 53 Punjabi
Apache-2.0
This is a Punjabi automatic speech recognition model fine-tuned on the Common Voice dataset based on Harveenchadha/vakyansh-wav2vec2-punjabi-pam-10
Speech Recognition Transformers Other
W
kingabzpro
189
2
Wav2vec2 Large Xls R 300m Kurdish
Apache-2.0
This is an automatic speech recognition (ASR) model fine-tuned on Kurmanji Kurdish datasets based on facebook/wav2vec2-xls-r-300m.
Speech Recognition Transformers Other
W
infinitejoy
81
4
Wav2vec2 Large Xlsr Coraa Portuguese Cv8
Apache-2.0
A Portuguese speech recognition model fine-tuned on the Common Voice dataset based on Edresson/wav2vec2-large-xlsr-coraa-portuguese
Speech Recognition Transformers
W
lgris
34
0
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
© 2025AIbase