wav2vec2 xls r 300m cv7 turkish Model description This ASR model is a fine tuned version of facebook/wav2vec2 xls r 300m on Turkish language. Training and evaluation data The following datasets were used for finetuning: Common Voice 7.0 TR All validated split except test split was used for training. MediaSpeech Training procedure To support both of the datasets above, custom pre processing and loading steps was performed and wav2vec2 turkish repo was used for that purpose. Training hyperparameters The following hypermaters were used for finetuning: learning rate 2e 4 num train epochs 10 warmup steps 500 freeze feature extractor mask time prob 0.1 mask feature prob 0.05 feat proj dropout 0.05 attention dropout 0.05 final dropout 0.05 activation dropout 0.05 per device train batch size 8 per device eval batch size 8 gradient accumulation steps 8 Framework versions Transformers 4.16.0.dev0 Pytorch 1.10.1 Datasets 1.17.0 Tokenizers 0.10.3 Language Model N gram language model is trained on a Turkish Wikipedia articles using KenLM and ngram lm wiki repo was used to generate arpa LM and convert it into binary format. Evaluation Commands Please install unicode tr package before running eva…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy