Baybars commited on
Commit
095bf84
1 Parent(s): e1c319e

Model save

Browse files
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "facebook/wav2vec2-xls-r-1b",
3
  "activation_dropout": 0.0,
4
  "adapter_kernel_size": 3,
5
  "adapter_stride": 2,
 
1
  {
2
+ "_name_or_path": "./checkpoint-10500",
3
  "activation_dropout": 0.0,
4
  "adapter_kernel_size": 3,
5
  "adapter_stride": 2,
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:518f88583acc237a9484294c5836ea827f4ca2979ddb5082958fd5251aec63e0
3
  size 3850522801
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ca4950372ef0c8087c4959170606fbc72ce4b0e560420df5686b99acb012d8c
3
  size 3850522801
run-initial.sh ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ python run_speech_recognition_ctc.py \
2
+ --dataset_name="common_voice" \
3
+ --model_name_or_path="facebook/wav2vec2-xls-r-1b" \
4
+ --dataset_config_name="tr" \
5
+ --output_dir="./" \
6
+ --overwrite_output_dir \
7
+ --num_train_epochs="100" \
8
+ --per_device_train_batch_size="32" \
9
+ --gradient_accumulation_steps="1" \
10
+ --learning_rate="5e-4" \
11
+ --warmup_steps="500" \
12
+ --evaluation_strategy="steps" \
13
+ --text_column_name="sentence" \
14
+ --save_steps="500" \
15
+ --eval_steps="500" \
16
+ --logging_steps="1" \
17
+ --layerdrop="0.0" \
18
+ --eval_metrics wer cer \
19
+ --save_total_limit="1" \
20
+ --mask_time_prob="0.3" \
21
+ --mask_time_length="10" \
22
+ --mask_feature_prob="0.1" \
23
+ --mask_feature_length="64" \
24
+ --chars_to_ignore , ? . ! - \; \: \" “ % ‘ ” � \
25
+ --fp16 \
26
+ --group_by_length \
27
+ --push_to_hub \
28
+ --do_train --do_eval \
29
+ --gradient_checkpointing \
30
+ --report_to tensorboard \
31
+ --use_auth_token
run.sh CHANGED
@@ -1,14 +1,16 @@
1
  python run_speech_recognition_ctc.py \
2
  --dataset_name="common_voice" \
3
- --model_name_or_path="facebook/wav2vec2-xls-r-1b" \
4
  --dataset_config_name="tr" \
5
  --output_dir="./" \
6
  --overwrite_output_dir \
7
- --num_train_epochs="100" \
8
  --per_device_train_batch_size="32" \
9
  --gradient_accumulation_steps="1" \
10
- --learning_rate="5e-4" \
11
- --warmup_steps="500" \
 
 
12
  --evaluation_strategy="steps" \
13
  --text_column_name="sentence" \
14
  --save_steps="500" \
 
1
  python run_speech_recognition_ctc.py \
2
  --dataset_name="common_voice" \
3
+ --model_name_or_path="./checkpoint-10500" \
4
  --dataset_config_name="tr" \
5
  --output_dir="./" \
6
  --overwrite_output_dir \
7
+ --num_train_epochs="5" \
8
  --per_device_train_batch_size="32" \
9
  --gradient_accumulation_steps="1" \
10
+ --learning_rate="2e-4" \
11
+ --adam_beta1="0.999" \
12
+ --adam_beta2="0.9999" \
13
+ --warmup_steps="0" \
14
  --evaluation_strategy="steps" \
15
  --text_column_name="sentence" \
16
  --save_steps="500" \
runs/Feb02_08-46-53_job-98a7eb1d-c6a6-4e4b-936b-3898557b5e73/1643791725.3471384/events.out.tfevents.1643791725.job-98a7eb1d-c6a6-4e4b-936b-3898557b5e73.544082.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6b29b1ae9c451e8eab2966f428b2e5c2a227492eeaaeca60368ca3af04965fc
3
+ size 4747
runs/Feb02_08-46-53_job-98a7eb1d-c6a6-4e4b-936b-3898557b5e73/events.out.tfevents.1643791725.job-98a7eb1d-c6a6-4e4b-936b-3898557b5e73.544082.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d1504af2a3148769c7c04d8660bb4d24066021036eb86bfa3a930478875ec83b
3
+ size 5009
special_tokens_map.json CHANGED
@@ -1 +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}]}
 
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}]}
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:322e8ae9f01b347bb69390fb3c42730bcf5c1f1587067d51096c85da5f6d9059
3
  size 2991
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8dee437aaa47d9cbc005e3b550051db80d4617488fe4076bffb7e191ee8a9d6
3
  size 2991