add training information

README.md

@@ -38,7 +38,56 @@ More information needed
 
 ## Training and evaluation data
 
-More information needed
+Training machine details
+
+- Platform: Linux-5.11.0-37-generic-x86_64-with-glibc2.10
+- CPU cores: 60
+- Python version: 3.8.8
+- PyTorch version: 1.10.1+cu102
+- GPU is visible: True
+- Transformers version: 4.16.0.dev0
+- Datasets version: 1.17.1.dev0
+- soundfile version: 0.10.3
+
+Training script
+
+```bash
+python run_speech_recognition_ctc.py \
+	--dataset_name="mozilla-foundation/common_voice_7_0" \
+	--model_name_or_path="facebook/wav2vec2-xls-r-300m" \
+	--dataset_config_name="or" \
+	--output_dir="./wav2vec2-large-xls-r-300m-odia" \
+	--overwrite_output_dir \
+	--num_train_epochs="120" \
+	--per_device_train_batch_size="16" \
+	--per_device_eval_batch_size="16" \
+	--gradient_accumulation_steps="2" \
+	--learning_rate="7.5e-5" \
+	--warmup_steps="500" \
+	--length_column_name="input_length" \
+	--evaluation_strategy="steps" \
+	--text_column_name="sentence" \
+	--chars_to_ignore , ? . ! \- \; \: \" “ % ‘ ” � — \’ … \– \' \’ \– \
+	--save_steps="500" \
+	--eval_steps="500" \
+	--logging_steps="100" \
+	--layerdrop="0.0" \
+	--activation_dropout="0.1" \
+	--save_total_limit="3" \
+	--freeze_feature_encoder \
+	--feat_proj_dropout="0.0" \
+	--mask_time_prob="0.75" \
+	--mask_time_length="10" \
+	--mask_feature_prob="0.25" \
+	--mask_feature_length="64" \
+	--gradient_checkpointing \
+	--use_auth_token \
+	--fp16 \
+	--group_by_length \
+	--do_train --do_eval \
+  --push_to_hub
+```
+    
 
 ## Training procedure