-
asr-africa/w2v-bert-2.0-CV_Fleurs_AMMI_ALFFA-sw-20hrs-v1
Automatic Speech Recognition • 0.6B • Updated -
asr-africa/w2v-bert-2.0-CV_Fleurs_AMMI_ALFFA-sw-10hrs-v1
Automatic Speech Recognition • 0.6B • Updated -
asr-africa/w2v-bert-2.0-CV_Fleurs_AMMI_ALFFA-sw-5hrs-v1
Automatic Speech Recognition • 0.6B • Updated -
asr-africa/w2v-bert-2.0-CV_Fleurs_AMMI_ALFFA-sw-1hrs-v1
Automatic Speech Recognition • 0.6B • Updated
ASR Africa
community
AI & ML interests
None defined yet.
Recent Activity
View all activity
-
asr-africa/whisper-small-CV-Fleurs-lg-20hrs-v1
Automatic Speech Recognition • 0.2B • Updated -
asr-africa/whisper-small-CV-Fleurs-lg-10hrs-v1
Automatic Speech Recognition • 0.2B • Updated -
asr-africa/whisper-small-CV-Fleurs-lg-5hrs-v1
Automatic Speech Recognition • 0.2B • Updated -
asr-africa/whisper-small-CV-Fleurs-lg-1hrs-v1
Automatic Speech Recognition • 0.2B • Updated
A collection of ASR models for the Zulu language. The models include Whisper Small, Wav2Vec2-BERT, MMS-1B, and Wav2Vec2 XLSR-300M architectures.
A collection of ASR models for the Afrikaans language. The models include Whisper Small, Wav2Vec2-BERT, MMS-1B, and Wav2Vec2 XLSR-300M architectures
A collection of ASR models for the Shona language. The models include Whisper Small, Wav2Vec2-BERT, MMS-1B, and Wav2Vec2 XLSR-300M architectures
-
asr-africa/wav2vec2_xls_r_300m_DigitalUmuganda_Afrivoice_Shona_5hr_v2
0.3B • Updated -
asr-africa/wav2vec2_xls_r_300m_DigitalUmuganda_Afrivoice_Shona_10hr_v5
0.3B • Updated -
asr-africa/wav2vec2_xls_r_300m_DigitalUmuganda_Afrivoice_Shona_50hr_v1
0.3B • Updated -
asr-africa/wav2vec2_xls_r_300m_DigitalUmuganda_Afrivoice_Shona_20hr_v2
0.3B • Updated
Collection of Finetuned ASR models trained on the Asheshi financial dataset
-
asr-africa/wav2vec2-asr-africa-base-fintuned-luganda-400hrs-v0.1
Automatic Speech Recognition • 0.1B • Updated • 10 -
asr-africa/wav2vec2-xls-r-asheshi-akan-10-hours
Automatic Speech Recognition • 0.3B • Updated -
asr-africa/wav2vec2-xls-r-asheshi-akan-5-hours
Automatic Speech Recognition • 0.3B • Updated -
asr-africa/wav2vec2-xls-r-asheshi-akan-1-hour
Automatic Speech Recognition • 0.3B • Updated • 1
-
asr-africa/wav2vec2-xls-r-300m-Fleurs_AMMI_AFRIVOICE_LRSC-ln-10hrs-v2
Automatic Speech Recognition • 0.3B • Updated -
asr-africa/wav2vec2-xls-r-300m-Fleurs_AMMI_AFRIVOICE_LRSC-ln-5hrs-v2
Automatic Speech Recognition • 0.3B • Updated -
asr-africa/wav2vec2-xls-r-300m-Fleurs_AMMI_AFRIVOICE_LRSC-ln-1hrs-v1
Automatic Speech Recognition • 0.3B • Updated
Collection of Wav2Vec2-XLS-R, W2V2-BERT and Whisper models trained on ALFFA dataset
-
asr-africa/wolof-1-hour-wav2vec2-xls-r-google-fleurs
Automatic Speech Recognition • 0.3B • Updated • 1 -
asr-africa/w2v2-bert-wolof-kallaama-42-hours
Automatic Speech Recognition • 0.6B • Updated • 6 -
asr-africa/w2v2-bert-wolof-mixed-75-hours
Automatic Speech Recognition • 0.6B • Updated • 4 -
asr-africa/w2v2_bert-Wolof-10-hours-alffa-plus-fleurs-dataset
Automatic Speech Recognition • 0.6B • Updated
A collection of ASR models for the Xhosa language. The models include Whisper Small, Wav2Vec2-BERT, MMS-1B, and Wav2Vec2 XLSR-300M architectures
A collection of ASR models for the Bemba language. The models include Whisper Small, Wav2Vec2-BERT, MMS-1B, and Wav2Vec2 XLSR-300M architectures
-
asr-africa/W2V2_Bert_BIG-C_BEMBA_10hr_v1
Automatic Speech Recognition • 0.6B • Updated -
asr-africa/w2v-bert-2.0_BIG-C_corpus_Bemba_1hr_v1
Automatic Speech Recognition • 0.6B • Updated -
asr-africa/wav2vec2_xls_r_300m_BIG-C_Bemba_100hr_v1
0.3B • Updated -
asr-africa/wav2vec2_xls_r_300m_BIG-C_Bemba_20hr_v5
0.3B • Updated
Collection of finetuned ASR models trained on increasing proportions of Fula language data.
-
asr-africa/w2v-bert-2.0-CV_Fleurs_AMMI_ALFFA-sw-20hrs-v1
Automatic Speech Recognition • 0.6B • Updated -
asr-africa/w2v-bert-2.0-CV_Fleurs_AMMI_ALFFA-sw-10hrs-v1
Automatic Speech Recognition • 0.6B • Updated -
asr-africa/w2v-bert-2.0-CV_Fleurs_AMMI_ALFFA-sw-5hrs-v1
Automatic Speech Recognition • 0.6B • Updated -
asr-africa/w2v-bert-2.0-CV_Fleurs_AMMI_ALFFA-sw-1hrs-v1
Automatic Speech Recognition • 0.6B • Updated
-
asr-africa/wav2vec2-xls-r-300m-Fleurs_AMMI_AFRIVOICE_LRSC-ln-10hrs-v2
Automatic Speech Recognition • 0.3B • Updated -
asr-africa/wav2vec2-xls-r-300m-Fleurs_AMMI_AFRIVOICE_LRSC-ln-5hrs-v2
Automatic Speech Recognition • 0.3B • Updated -
asr-africa/wav2vec2-xls-r-300m-Fleurs_AMMI_AFRIVOICE_LRSC-ln-1hrs-v1
Automatic Speech Recognition • 0.3B • Updated
-
asr-africa/whisper-small-CV-Fleurs-lg-20hrs-v1
Automatic Speech Recognition • 0.2B • Updated -
asr-africa/whisper-small-CV-Fleurs-lg-10hrs-v1
Automatic Speech Recognition • 0.2B • Updated -
asr-africa/whisper-small-CV-Fleurs-lg-5hrs-v1
Automatic Speech Recognition • 0.2B • Updated -
asr-africa/whisper-small-CV-Fleurs-lg-1hrs-v1
Automatic Speech Recognition • 0.2B • Updated
Collection of Wav2Vec2-XLS-R, W2V2-BERT and Whisper models trained on ALFFA dataset
-
asr-africa/wolof-1-hour-wav2vec2-xls-r-google-fleurs
Automatic Speech Recognition • 0.3B • Updated • 1 -
asr-africa/w2v2-bert-wolof-kallaama-42-hours
Automatic Speech Recognition • 0.6B • Updated • 6 -
asr-africa/w2v2-bert-wolof-mixed-75-hours
Automatic Speech Recognition • 0.6B • Updated • 4 -
asr-africa/w2v2_bert-Wolof-10-hours-alffa-plus-fleurs-dataset
Automatic Speech Recognition • 0.6B • Updated
A collection of ASR models for the Zulu language. The models include Whisper Small, Wav2Vec2-BERT, MMS-1B, and Wav2Vec2 XLSR-300M architectures.
A collection of ASR models for the Xhosa language. The models include Whisper Small, Wav2Vec2-BERT, MMS-1B, and Wav2Vec2 XLSR-300M architectures
A collection of ASR models for the Afrikaans language. The models include Whisper Small, Wav2Vec2-BERT, MMS-1B, and Wav2Vec2 XLSR-300M architectures
A collection of ASR models for the Bemba language. The models include Whisper Small, Wav2Vec2-BERT, MMS-1B, and Wav2Vec2 XLSR-300M architectures
-
asr-africa/W2V2_Bert_BIG-C_BEMBA_10hr_v1
Automatic Speech Recognition • 0.6B • Updated -
asr-africa/w2v-bert-2.0_BIG-C_corpus_Bemba_1hr_v1
Automatic Speech Recognition • 0.6B • Updated -
asr-africa/wav2vec2_xls_r_300m_BIG-C_Bemba_100hr_v1
0.3B • Updated -
asr-africa/wav2vec2_xls_r_300m_BIG-C_Bemba_20hr_v5
0.3B • Updated
A collection of ASR models for the Shona language. The models include Whisper Small, Wav2Vec2-BERT, MMS-1B, and Wav2Vec2 XLSR-300M architectures
-
asr-africa/wav2vec2_xls_r_300m_DigitalUmuganda_Afrivoice_Shona_5hr_v2
0.3B • Updated -
asr-africa/wav2vec2_xls_r_300m_DigitalUmuganda_Afrivoice_Shona_10hr_v5
0.3B • Updated -
asr-africa/wav2vec2_xls_r_300m_DigitalUmuganda_Afrivoice_Shona_50hr_v1
0.3B • Updated -
asr-africa/wav2vec2_xls_r_300m_DigitalUmuganda_Afrivoice_Shona_20hr_v2
0.3B • Updated
Collection of finetuned ASR models trained on increasing proportions of Fula language data.
Collection of Finetuned ASR models trained on the Asheshi financial dataset
-
asr-africa/wav2vec2-asr-africa-base-fintuned-luganda-400hrs-v0.1
Automatic Speech Recognition • 0.1B • Updated • 10 -
asr-africa/wav2vec2-xls-r-asheshi-akan-10-hours
Automatic Speech Recognition • 0.3B • Updated -
asr-africa/wav2vec2-xls-r-asheshi-akan-5-hours
Automatic Speech Recognition • 0.3B • Updated -
asr-africa/wav2vec2-xls-r-asheshi-akan-1-hour
Automatic Speech Recognition • 0.3B • Updated • 1