patrickvonplaten
/

wav2vec2-xls-r-phoneme-300m-tr

Automatic Speech Recognition

Generated from Trainer

Inference Endpoints

Model card Files Files and versions Metrics Training metrics Community

patrickvonplaten commited on Dec 10, 2021

Commit

a19ef19

·

1 Parent(s): 2584f56

Update run.sh

Files changed (1) hide show

run.sh +1 -1

run.sh CHANGED Viewed

@@ -2,7 +2,7 @@
 python -m torch.distributed.launch \
         --nproc_per_node 2 run_speech_recognition_ctc.py \
         --dataset_name="common_voice" \
-        --model_name_or_path="./wav2vec2-xls-r-phoneme-300m-tr" \
 				--tokenizer_name_or_path="./wav2vec2-xls-r-phoneme-300m-tr" \
         --dataset_config_name="tr" \
 				--phoneme_language="tr" \

 python -m torch.distributed.launch \
         --nproc_per_node 2 run_speech_recognition_ctc.py \
         --dataset_name="common_voice" \
+        --model_name_or_path="facebook/wav2vec2-xlsr-53-espeak-cv-ft" \
 				--tokenizer_name_or_path="./wav2vec2-xls-r-phoneme-300m-tr" \
         --dataset_config_name="tr" \
 				--phoneme_language="tr" \