Training in progress, step 500

.ipynb_checkpoints/mozilla-foundation_common_voice_8_0_ky_test_eval_results-checkpoint.txt

@@ -0,0 +1,2 @@
+WER: 0.31282098312545853
+CER: 0.07663251646764126

.ipynb_checkpoints/run-checkpoint.sh

@@ -2,11 +2,11 @@ python ~/xls-r-kyrgiz-cv8/run_speech_recognition_ctc.py \
 	--dataset_name="mozilla-foundation/common_voice_8_0" \
 	--model_name_or_path="facebook/wav2vec2-xls-r-300m" \
 	--dataset_config_name="ky" \
-    --train_split_name="train+validation[:50%]" \
-    --eval_split_name="validation[50%:]" \
+    --train_split_name="train+validation+other" \
+    --eval_split_name="test[50%:]" \
 	--output_dir="~/xls-r-kyrgiz-cv8" \
 	--overwrite_output_dir \
-	--num_train_epochs="400" \
+	--num_train_epochs="300" \
 	--per_device_train_batch_size="32" \
 	--per_device_eval_batch_size="8" \
 	--gradient_accumulation_steps="4" \
@@ -16,19 +16,19 @@ python ~/xls-r-kyrgiz-cv8/run_speech_recognition_ctc.py \
 	--evaluation_strategy="steps" \
 	--text_column_name="sentence" \
 	--chars_to_ignore , ? . ! \- \; \: \\ _ \| ‒ ☺ ♂ © « ¬ » \" „ “ % ” �  — ’ ، ؛ ؟ ‹ › − … – \
-	--eval_metrics="wer" \
+	--eval_metrics wer cer \
 	--save_steps="500" \
 	--eval_steps="500" \
 	--logging_steps="100" \
 	--min_duration_in_seconds="0.2" \
-	--layerdrop="0.01" \
+	--layerdrop="0.0" \
 	--activation_dropout="0.1" \
 	--save_total_limit="3" \
 	--freeze_feature_encoder \
 	--feat_proj_dropout="0.01" \
 	--mask_time_prob="0.50" \
 	--mask_time_length="10" \
-	--mask_feature_prob="0.25" \
+	--mask_feature_prob="0.4" \
 	--mask_feature_length="64" \
 	--gradient_checkpointing \
 	--use_auth_token \

config.json

@@ -58,10 +58,10 @@
   "initializer_range": 0.02,
   "intermediate_size": 4096,
   "layer_norm_eps": 1e-05,
-  "layerdrop": 0.01,
+  "layerdrop": 0.0,
   "mask_feature_length": 64,
   "mask_feature_min_masks": 0,
-  "mask_feature_prob": 0.25,
+  "mask_feature_prob": 0.4,
   "mask_time_length": 10,
   "mask_time_min_masks": 2,
   "mask_time_prob": 0.5,

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:558db79d78093393e165bc72a9670c8936ce2ab92f721b46d0c247eb128fe89b
+oid sha256:e8dc2cfa0eff32907f7b3e1700f723eb02ccfbc100c03c38d7bf6d75f25e8565
 size 1262095857

run.sh

@@ -2,11 +2,11 @@ python ~/xls-r-kyrgiz-cv8/run_speech_recognition_ctc.py \
 	--dataset_name="mozilla-foundation/common_voice_8_0" \
 	--model_name_or_path="facebook/wav2vec2-xls-r-300m" \
 	--dataset_config_name="ky" \
-    --train_split_name="train+validation[:50%]" \
-    --eval_split_name="validation[50%:]" \
+    --train_split_name="train+validation+other" \
+    --eval_split_name="test[50%:]" \
 	--output_dir="~/xls-r-kyrgiz-cv8" \
 	--overwrite_output_dir \
-	--num_train_epochs="400" \
+	--num_train_epochs="300" \
 	--per_device_train_batch_size="32" \
 	--per_device_eval_batch_size="8" \
 	--gradient_accumulation_steps="4" \
@@ -16,19 +16,19 @@ python ~/xls-r-kyrgiz-cv8/run_speech_recognition_ctc.py \
 	--evaluation_strategy="steps" \
 	--text_column_name="sentence" \
 	--chars_to_ignore , ? . ! \- \; \: \\ _ \| ‒ ☺ ♂ © « ¬ » \" „ “ % ” �  — ’ ، ؛ ؟ ‹ › − … – \
-	--eval_metrics="wer" \
+	--eval_metrics wer cer \
 	--save_steps="500" \
 	--eval_steps="500" \
 	--logging_steps="100" \
 	--min_duration_in_seconds="0.2" \
-	--layerdrop="0.01" \
+	--layerdrop="0.0" \
 	--activation_dropout="0.1" \
 	--save_total_limit="3" \
 	--freeze_feature_encoder \
 	--feat_proj_dropout="0.01" \
 	--mask_time_prob="0.50" \
 	--mask_time_length="10" \
-	--mask_feature_prob="0.25" \
+	--mask_feature_prob="0.4" \
 	--mask_feature_length="64" \
 	--gradient_checkpointing \
 	--use_auth_token \

runs/Feb05_21-45-17_job-699ba53c-fea9-4eb2-81af-a97f440eaa45/1644097571.4686165/events.out.tfevents.1644097571.job-699ba53c-fea9-4eb2-81af-a97f440eaa45.2077552.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aec5c9bfe83fac7fcd98acde05ce85aa7a981132e4299d52fc1c40e06bace6e9
+size 4829

runs/Feb05_21-45-17_job-699ba53c-fea9-4eb2-81af-a97f440eaa45/events.out.tfevents.1644097571.job-699ba53c-fea9-4eb2-81af-a97f440eaa45.2077552.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef57ddb22dc8090ed5778c2b12a2e70a92c8657a552e2725c94afc9b4578a8a4
+size 5929

special_tokens_map.json

@@ -1 +1 @@
-{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "pad_token": "[PAD]", "additional_special_tokens": [{"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}]}
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "pad_token": "[PAD]", "additional_special_tokens": [{"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}]}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78a4ea01b60c27365021cbdc9621863e802fedd869c9f5fe4c5e4182a4829377
+oid sha256:e5aa32cf8615d4a9dfa30aa360c71b8bbb63969088668bb62da942e0cb4353cd
 size 3055