patrickvonplaten
/

wav2vec2-xls-r-phoneme-300m-sv

Automatic Speech Recognition Transformers PyTorch TensorBoard

Swedish wav2vec2 common_voice generated_from_trainer Inference Endpoints

Model card Files Files and versions Metrics Training metrics Community

patrickvonplaten commited on Dec 10, 2021

Commit

54e90f0

•

1 Parent(s): 0ab3fb9

Update README.md

Files changed (1) hide show

README.md +4 -0

README.md CHANGED Viewed

@@ -17,6 +17,10 @@ should probably proofread and complete it, then remove this comment. -->
 # Wav2vec2-xls-r-phoneme-300m-sv
 This model is a fine-tuned version of [wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the COMMON_VOICE - SV-SE dataset.
 It achieves the following results on the evaluation set:

 # Wav2vec2-xls-r-phoneme-300m-sv
+**Note**: The tokenizer was created from the official Swedish phoneme vocabulary as defined here: https://github.com/microsoft/UniSpeech/blob/main/UniSpeech/examples/unispeech/data/sv/phonesMatches_reduced.json
+One can simply download the file, rename it to `vocab.json` and load a `Wav2Vec2PhonemeCTCTokenizer.from_pretrained("./directory/with/vocab.json/")`.
 This model is a fine-tuned version of [wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the COMMON_VOICE - SV-SE dataset.
 It achieves the following results on the evaluation set: