Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
Safetensors
French
wav2vec2
hf-asr-leaderboard
robust-speech-event
CTC
Wav2vec2
Eval Results (legacy)
Instructions to use bofenghuang/asr-wav2vec2-ctc-french with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use bofenghuang/asr-wav2vec2-ctc-french with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="bofenghuang/asr-wav2vec2-ctc-french")# Load model directly from transformers import AutoProcessor, AutoModelForCTC processor = AutoProcessor.from_pretrained("bofenghuang/asr-wav2vec2-ctc-french") model = AutoModelForCTC.from_pretrained("bofenghuang/asr-wav2vec2-ctc-french", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Ctrl+K
- language_model
- results_african_accented_french
- results_african_accented_french_with_lm
- results_facebook_voxpopuli
- results_facebook_voxpopuli_with_lm
- results_google_fleurs
- results_google_fleurs_with_lm
- results_mozilla-foundatio_common_voice_11_0
- results_mozilla-foundatio_common_voice_11_0_with_lm
- results_multilingual_librispeech
- results_multilingual_librispeech_with_lm
- results_speech-recognition-community-v2_dev_data
- results_speech-recognition-community-v2_dev_data_chunk30_stride5
- results_speech-recognition-community-v2_dev_data_with_lm
- results_speech-recognition-community-v2_dev_data_with_lm_chunk30_stride5
- runs
- 1.48 kB
- 6.37 kB
- 30 Bytes
- 373 Bytes
- 2.28 kB
- 6.2 kB
- 1.26 GB xet
- 262 Bytes
- 1.26 GB xet
- 4.5 kB
- 431 Bytes
- 546 Bytes