clean

.ipynb_checkpoints/README-checkpoint.md

@@ -1,158 +0,0 @@
----
-language:
-- ca
-license: apache-2.0
-tags:
-- automatic-speech-recognition
-- mozilla-foundation/common_voice_8_0
-- collectivat/tv3_parla
-- projecte-aina/parlament_parla
-- generated_from_trainer
-- robust-speech-event
-datasets:
-- mozilla-foundation/common_voice_8_0
-- collectivat/tv3_parla
-- projecte-aina/parlament_parla
-model-index:
-- name: wav2vec2-xls-r-300m-ca
-  results:
-  - task: 
-      name: Speech Recognition
-      type: automatic-speech-recognition
-    dataset:
-      name: mozilla-foundation/common_voice_8_0 ca
-      type: mozilla-foundation/common_voice_8_0
-      args: ca
-    metrics:
-       - name: Test WER
-         type: wer
-         value: 0.15636874077301
-       - name: Test CER
-         type: cer
-         value: 0.04086725403909639
-  - task: 
-      name: Speech Recognition
-      type: automatic-speech-recognition
-    dataset:
-      name: projecte-aina/parlament_parla ca
-      type: projecte-aina/parlament_parla
-      args: clean
-    metrics:
-       - name: Test WER
-         type: wer
-         value: 0.09940385143350199
-       - name: Test CER
-         type: cer
-         value: 0.026906712890009454
-  - task: 
-      name: Speech Recognition
-      type: automatic-speech-recognition
-    dataset:
-      name: collectivat/tv3_parla ca
-      type: collectivat/tv3_parla
-      args: ca
-    metrics:
-       - name: Test WER
-         type: wer
-         value: 0.27349193517342263
-       - name: Test CER
-         type: cer
-         value: 0.11571091827304163
----
-
-<!-- This model card has been generated automatically according to the information the Trainer had access to. You
-should probably proofread and complete it, then remove this comment. -->
-
-# wav2vec2-xls-r-300m-ca
-
-This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the MOZILLA-FOUNDATION/COMMON_VOICE_8_0 - CA dataset.
-It achieves the following results on the evaluation set:
-- Loss: 0.2549
-- Wer: 0.1573
-
-## Model description
-
-More information needed
-
-## Intended uses & limitations
-
-More information needed
-
-## Training and evaluation data
-
-More information needed
-
-## Training procedure
-
-### Training hyperparameters
-
-The following hyperparameters were used during training:
-- learning_rate: 7.5e-05
-- train_batch_size: 32
-- eval_batch_size: 32
-- seed: 42
-- gradient_accumulation_steps: 4
-- total_train_batch_size: 128
-- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
-- lr_scheduler_type: linear
-- lr_scheduler_warmup_steps: 2000
-- num_epochs: 12.0
-- mixed_precision_training: Native AMP
-
-### Training results
-
-| Training Loss | Epoch | Step  | Validation Loss | Wer    |
-|:-------------:|:-----:|:-----:|:---------------:|:------:|
-| 6.2099        | 0.09  | 500   | 3.4125          | 1.0    |
-| 2.9961        | 0.18  | 1000  | 2.9224          | 1.0    |
-| 2.2147        | 0.26  | 1500  | 0.6521          | 0.5568 |
-| 1.3017        | 0.35  | 2000  | 0.3153          | 0.2761 |
-| 1.1196        | 0.44  | 2500  | 0.2444          | 0.2367 |
-| 1.0712        | 0.53  | 3000  | 0.2324          | 0.2132 |
-| 1.052         | 0.62  | 3500  | 0.2173          | 0.2032 |
-| 1.2813        | 2.13  | 4000  | 0.3326          | 0.2099 |
-| 1.2365        | 2.4   | 4500  | 0.3224          | 0.2003 |
-| 1.2193        | 2.66  | 5000  | 0.3198          | 0.1957 |
-| 1.2072        | 2.93  | 5500  | 0.3063          | 0.1933 |
-| 1.213         | 3.2   | 6000  | 0.3051          | 0.1980 |
-| 1.2074        | 3.46  | 6500  | 0.3012          | 0.1879 |
-| 1.1918        | 3.73  | 7000  | 0.2947          | 0.1829 |
-| 1.1893        | 4.0   | 7500  | 0.2895          | 0.1807 |
-| 1.1751        | 4.26  | 8000  | 0.2878          | 0.1776 |
-| 1.1628        | 4.53  | 8500  | 0.2835          | 0.1731 |
-| 1.1577        | 4.79  | 9000  | 0.2816          | 0.1761 |
-| 1.1448        | 5.06  | 9500  | 0.2757          | 0.1740 |
-| 1.1407        | 5.33  | 10000 | 0.2768          | 0.1798 |
-| 1.1401        | 5.59  | 10500 | 0.2780          | 0.1816 |
-| 1.1333        | 5.86  | 11000 | 0.2748          | 0.1750 |
-| 1.1571        | 6.13  | 11500 | 0.2808          | 0.1708 |
-| 1.1505        | 6.39  | 12000 | 0.2726          | 0.1692 |
-| 1.1519        | 6.66  | 12500 | 0.2749          | 0.1654 |
-| 1.136         | 6.93  | 13000 | 0.2765          | 0.1643 |
-| 1.1326        | 7.19  | 13500 | 0.2706          | 0.1668 |
-| 1.1342        | 7.46  | 14000 | 0.2665          | 0.1638 |
-| 1.1286        | 7.72  | 14500 | 0.2669          | 0.1636 |
-| 1.1243        | 7.99  | 15000 | 0.2619          | 0.1623 |
-| 1.1173        | 8.26  | 15500 | 0.2652          | 0.1604 |
-| 1.1129        | 8.52  | 16000 | 0.2610          | 0.1598 |
-| 1.1091        | 8.79  | 16500 | 0.2608          | 0.1584 |
-| 1.1053        | 9.06  | 17000 | 0.2633          | 0.1664 |
-| 1.1004        | 9.32  | 17500 | 0.2594          | 0.1662 |
-| 1.0995        | 9.59  | 18000 | 0.2623          | 0.1569 |
-| 1.0964        | 9.86  | 18500 | 0.2624          | 0.1597 |
-| 1.09          | 10.12 | 19000 | 0.2577          | 0.1578 |
-| 1.089         | 10.39 | 19500 | 0.2574          | 0.1531 |
-| 1.0864        | 10.66 | 20000 | 0.2556          | 0.1546 |
-| 1.0806        | 10.92 | 20500 | 0.2548          | 0.1583 |
-| 1.0842        | 11.19 | 21000 | 0.2550          | 0.1542 |
-| 1.0805        | 11.45 | 21500 | 0.2561          | 0.1524 |
-| 1.0722        | 11.72 | 22000 | 0.2540          | 0.1566 |
-| 1.0763        | 11.99 | 22500 | 0.2549          | 0.1572 |
-
-
-### Framework versions
-
-- Transformers 4.16.0.dev0
-- Pytorch 1.10.1+cu102
-- Datasets 1.18.1
-- Tokenizers 0.11.0

.ipynb_checkpoints/all_results-checkpoint.json

@@ -1,14 +0,0 @@
-{
-    "epoch": 12.0,
-    "eval_loss": 0.25491979718208313,
-    "eval_runtime": 392.0567,
-    "eval_samples": 4297,
-    "eval_samples_per_second": 10.96,
-    "eval_steps_per_second": 0.344,
-    "eval_wer": 0.15725760362438562,
-    "train_loss": 0.5676147035501541,
-    "train_runtime": 172546.67,
-    "train_samples": 240334,
-    "train_samples_per_second": 16.714,
-    "train_steps_per_second": 0.131
-}

.ipynb_checkpoints/eval_results-checkpoint.json

@@ -1,9 +0,0 @@
-{
-    "epoch": 12.0,
-    "eval_loss": 0.25491979718208313,
-    "eval_runtime": 392.0567,
-    "eval_samples": 4297,
-    "eval_samples_per_second": 10.96,
-    "eval_steps_per_second": 0.344,
-    "eval_wer": 0.15725760362438562
-}

.ipynb_checkpoints/run-checkpoint.sh

@@ -1,39 +0,0 @@
-python run_speech_recognition_ctc.py \
---dataset_name "mozilla-foundation/common_voice_8_0" "collectivat/tv3_parla" "projecte-aina/parlament_parla" \
---dataset_config_name "ca" "ca" "clean" \
---model_name_or_path="facebook/wav2vec2-xls-r-300m" \
---train_split_name "train+validation" "train" "train+validation" \
---eval_split_name "test" "test" "test" \
---audio_column_name "audio" "audio" "audio" \
---output_dir="wav2vec2-xls-r-300m-ca" \
---overwrite_output_dir \
---num_train_epochs="10" \
---per_device_train_batch_size="32" \
---per_device_eval_batch_size="32" \
---gradient_accumulation_steps="4" \
---learning_rate="7.5e-5" \
---warmup_steps="2000" \
---length_column_name="input_length" \
---evaluation_strategy="steps" \
---text_column_name "sentence" "text" "sentence" \
---chars_to_ignore [ , ? . ! \; \: \" “ % ” � — … – ] \
---save_steps="500" \
---eval_steps="500" \
---logging_steps="500" \
---layerdrop="0.0" \
---activation_dropout="0.1" \
---save_total_limit="3" \
---freeze_feature_encoder \
---feat_proj_dropout="0.0" \
---mask_time_prob="0.75" \
---preprocessing_num_workers="12" \
---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 
-#&> train.log

.ipynb_checkpoints/train_results-checkpoint.json

@@ -1,8 +0,0 @@
-{
-    "epoch": 12.0,
-    "train_loss": 0.5676147035501541,
-    "train_runtime": 172546.67,
-    "train_samples": 240334,
-    "train_samples_per_second": 16.714,
-    "train_steps_per_second": 0.131
-}

.ipynb_checkpoints/trainer_state-checkpoint.json

@@ -1,700 +0,0 @@
-{
-  "best_metric": null,
-  "best_model_checkpoint": null,
-  "epoch": 11.999600585807482,
-  "global_step": 22524,
-  "is_hyper_param_search": false,
-  "is_local_process_zero": true,
-  "is_world_process_zero": true,
-  "log_history": [
-    {
-      "epoch": 0.09,
-      "learning_rate": 1.8712499999999997e-05,
-      "loss": 6.2099,
-      "step": 500
-    },
-    {
-      "epoch": 0.09,
-      "eval_loss": 3.41253662109375,
-      "eval_runtime": 1358.074,
-      "eval_samples_per_second": 14.868,
-      "eval_steps_per_second": 0.465,
-      "eval_wer": 1.0,
-      "step": 500
-    },
-    {
-      "epoch": 0.18,
-      "learning_rate": 3.7462499999999996e-05,
-      "loss": 2.9961,
-      "step": 1000
-    },
-    {
-      "epoch": 0.18,
-      "eval_loss": 2.9223873615264893,
-      "eval_runtime": 1361.8836,
-      "eval_samples_per_second": 14.827,
-      "eval_steps_per_second": 0.463,
-      "eval_wer": 1.0,
-      "step": 1000
-    },
-    {
-      "epoch": 0.26,
-      "learning_rate": 5.62125e-05,
-      "loss": 2.2147,
-      "step": 1500
-    },
-    {
-      "epoch": 0.26,
-      "eval_loss": 0.6520791053771973,
-      "eval_runtime": 1355.9385,
-      "eval_samples_per_second": 14.892,
-      "eval_steps_per_second": 0.465,
-      "eval_wer": 0.5567824255052013,
-      "step": 1500
-    },
-    {
-      "epoch": 0.35,
-      "learning_rate": 7.49625e-05,
-      "loss": 1.3017,
-      "step": 2000
-    },
-    {
-      "epoch": 0.35,
-      "eval_loss": 0.31525641679763794,
-      "eval_runtime": 1371.0684,
-      "eval_samples_per_second": 14.727,
-      "eval_steps_per_second": 0.46,
-      "eval_wer": 0.27607269814249236,
-      "step": 2000
-    },
-    {
-      "epoch": 0.44,
-      "learning_rate": 7.431581352833637e-05,
-      "loss": 1.1196,
-      "step": 2500
-    },
-    {
-      "epoch": 0.44,
-      "eval_loss": 0.24444133043289185,
-      "eval_runtime": 1363.4869,
-      "eval_samples_per_second": 14.809,
-      "eval_steps_per_second": 0.463,
-      "eval_wer": 0.23673497683411066,
-      "step": 2500
-    },
-    {
-      "epoch": 0.53,
-      "learning_rate": 7.363162705667275e-05,
-      "loss": 1.0712,
-      "step": 3000
-    },
-    {
-      "epoch": 0.53,
-      "eval_loss": 0.23236490786075592,
-      "eval_runtime": 1368.4487,
-      "eval_samples_per_second": 14.755,
-      "eval_steps_per_second": 0.461,
-      "eval_wer": 0.21321861436015543,
-      "step": 3000
-    },
-    {
-      "epoch": 0.62,
-      "learning_rate": 7.294606946983546e-05,
-      "loss": 1.052,
-      "step": 3500
-    },
-    {
-      "epoch": 0.62,
-      "eval_loss": 0.21734564006328583,
-      "eval_runtime": 1358.6503,
-      "eval_samples_per_second": 14.862,
-      "eval_steps_per_second": 0.464,
-      "eval_wer": 0.20317428528513493,
-      "step": 3500
-    },
-    {
-      "epoch": 2.13,
-      "learning_rate": 3.375103277334068e-05,
-      "loss": 1.2813,
-      "step": 4000
-    },
-    {
-      "epoch": 2.13,
-      "eval_loss": 0.332599401473999,
-      "eval_runtime": 393.989,
-      "eval_samples_per_second": 10.906,
-      "eval_steps_per_second": 0.343,
-      "eval_wer": 0.20989847979467358,
-      "step": 4000
-    },
-    {
-      "epoch": 2.4,
-      "learning_rate": 2.3423299366565682e-05,
-      "loss": 1.2365,
-      "step": 4500
-    },
-    {
-      "epoch": 2.4,
-      "eval_loss": 0.3223731815814972,
-      "eval_runtime": 391.7507,
-      "eval_samples_per_second": 10.969,
-      "eval_steps_per_second": 0.345,
-      "eval_wer": 0.2003283560376986,
-      "step": 4500
-    },
-    {
-      "epoch": 2.66,
-      "learning_rate": 1.309556595979069e-05,
-      "loss": 1.2193,
-      "step": 5000
-    },
-    {
-      "epoch": 2.66,
-      "eval_loss": 0.31981074810028076,
-      "eval_runtime": 402.4439,
-      "eval_samples_per_second": 10.677,
-      "eval_steps_per_second": 0.335,
-      "eval_wer": 0.19565239980464894,
-      "step": 5000
-    },
-    {
-      "epoch": 2.93,
-      "learning_rate": 2.767832553015698e-06,
-      "loss": 1.2072,
-      "step": 5500
-    },
-    {
-      "epoch": 2.93,
-      "eval_loss": 0.3063456118106842,
-      "eval_runtime": 396.6525,
-      "eval_samples_per_second": 10.833,
-      "eval_steps_per_second": 0.34,
-      "eval_wer": 0.19327285763271923,
-      "step": 5500
-    },
-    {
-      "epoch": 3.2,
-      "learning_rate": 4.263388037141005e-05,
-      "loss": 1.213,
-      "step": 6000
-    },
-    {
-      "epoch": 3.2,
-      "eval_loss": 0.3051116168498993,
-      "eval_runtime": 371.5477,
-      "eval_samples_per_second": 11.565,
-      "eval_steps_per_second": 0.363,
-      "eval_wer": 0.19797998690732255,
-      "step": 6000
-    },
-    {
-      "epoch": 3.46,
-      "learning_rate": 3.8585078816670256e-05,
-      "loss": 1.2074,
-      "step": 6500
-    },
-    {
-      "epoch": 3.46,
-      "eval_loss": 0.3011966645717621,
-      "eval_runtime": 372.0587,
-      "eval_samples_per_second": 11.549,
-      "eval_steps_per_second": 0.363,
-      "eval_wer": 0.18792148549934018,
-      "step": 6500
-    },
-    {
-      "epoch": 3.73,
-      "learning_rate": 3.4536277261930465e-05,
-      "loss": 1.1918,
-      "step": 7000
-    },
-    {
-      "epoch": 3.73,
-      "eval_loss": 0.29471954703330994,
-      "eval_runtime": 372.8767,
-      "eval_samples_per_second": 11.524,
-      "eval_steps_per_second": 0.362,
-      "eval_wer": 0.18287145276764655,
-      "step": 7000
-    },
-    {
-      "epoch": 4.0,
-      "learning_rate": 3.0487475707190668e-05,
-      "loss": 1.1893,
-      "step": 7500
-    },
-    {
-      "epoch": 4.0,
-      "eval_loss": 0.28953900933265686,
-      "eval_runtime": 372.4558,
-      "eval_samples_per_second": 11.537,
-      "eval_steps_per_second": 0.362,
-      "eval_wer": 0.1807205129004437,
-      "step": 7500
-    },
-    {
-      "epoch": 4.26,
-      "learning_rate": 2.643867415245087e-05,
-      "loss": 1.1751,
-      "step": 8000
-    },
-    {
-      "epoch": 4.26,
-      "eval_loss": 0.2877567410469055,
-      "eval_runtime": 371.9244,
-      "eval_samples_per_second": 11.553,
-      "eval_steps_per_second": 0.363,
-      "eval_wer": 0.17759281773122604,
-      "step": 8000
-    },
-    {
-      "epoch": 4.53,
-      "learning_rate": 2.2389872597711073e-05,
-      "loss": 1.1628,
-      "step": 8500
-    },
-    {
-      "epoch": 4.53,
-      "eval_loss": 0.28352275490760803,
-      "eval_runtime": 373.4388,
-      "eval_samples_per_second": 11.507,
-      "eval_steps_per_second": 0.362,
-      "eval_wer": 0.1730727267059447,
-      "step": 8500
-    },
-    {
-      "epoch": 4.79,
-      "learning_rate": 1.834107104297128e-05,
-      "loss": 1.1577,
-      "step": 9000
-    },
-    {
-      "epoch": 4.79,
-      "eval_loss": 0.28156954050064087,
-      "eval_runtime": 371.5997,
-      "eval_samples_per_second": 11.564,
-      "eval_steps_per_second": 0.363,
-      "eval_wer": 0.17605494768124527,
-      "step": 9000
-    },
-    {
-      "epoch": 5.06,
-      "learning_rate": 1.4300367091340963e-05,
-      "loss": 1.1448,
-      "step": 9500
-    },
-    {
-      "epoch": 5.06,
-      "eval_loss": 0.2757455110549927,
-      "eval_runtime": 373.7148,
-      "eval_samples_per_second": 11.498,
-      "eval_steps_per_second": 0.361,
-      "eval_wer": 0.17397674491100096,
-      "step": 9500
-    },
-    {
-      "epoch": 5.33,
-      "learning_rate": 1.0251565536601165e-05,
-      "loss": 1.1407,
-      "step": 10000
-    },
-    {
-      "epoch": 5.33,
-      "eval_loss": 0.2768358588218689,
-      "eval_runtime": 373.2273,
-      "eval_samples_per_second": 11.513,
-      "eval_steps_per_second": 0.362,
-      "eval_wer": 0.17976453962613131,
-      "step": 10000
-    },
-    {
-      "epoch": 5.59,
-      "learning_rate": 6.202763981861369e-06,
-      "loss": 1.1401,
-      "step": 10500
-    },
-    {
-      "epoch": 5.59,
-      "eval_loss": 0.2780420780181885,
-      "eval_runtime": 375.3753,
-      "eval_samples_per_second": 11.447,
-      "eval_steps_per_second": 0.36,
-      "eval_wer": 0.18160374907779753,
-      "step": 10500
-    },
-    {
-      "epoch": 5.86,
-      "learning_rate": 2.153962427121572e-06,
-      "loss": 1.1333,
-      "step": 11000
-    },
-    {
-      "epoch": 5.86,
-      "eval_loss": 0.2748132646083832,
-      "eval_runtime": 371.6352,
-      "eval_samples_per_second": 11.562,
-      "eval_steps_per_second": 0.363,
-      "eval_wer": 0.17495350021301578,
-      "step": 11000
-    },
-    {
-      "epoch": 6.13,
-      "learning_rate": 4.029916195673358e-05,
-      "loss": 1.1571,
-      "step": 11500
-    },
-    {
-      "epoch": 6.13,
-      "eval_loss": 0.2807982861995697,
-      "eval_runtime": 393.9701,
-      "eval_samples_per_second": 10.907,
-      "eval_steps_per_second": 0.343,
-      "eval_wer": 0.17083865872793208,
-      "step": 11500
-    },
-    {
-      "epoch": 6.39,
-      "learning_rate": 3.8472032742155524e-05,
-      "loss": 1.1505,
-      "step": 12000
-    },
-    {
-      "epoch": 6.39,
-      "eval_loss": 0.27258625626564026,
-      "eval_runtime": 389.5937,
-      "eval_samples_per_second": 11.029,
-      "eval_steps_per_second": 0.347,
-      "eval_wer": 0.16920726955329032,
-      "step": 12000
-    },
-    {
-      "epoch": 6.66,
-      "learning_rate": 3.6648557786006625e-05,
-      "loss": 1.1519,
-      "step": 12500
-    },
-    {
-      "epoch": 6.66,
-      "eval_loss": 0.2748955190181732,
-      "eval_runtime": 387.583,
-      "eval_samples_per_second": 11.087,
-      "eval_steps_per_second": 0.348,
-      "eval_wer": 0.16539376746989204,
-      "step": 12500
-    },
-    {
-      "epoch": 6.93,
-      "learning_rate": 3.482142857142857e-05,
-      "loss": 1.136,
-      "step": 13000
-    },
-    {
-      "epoch": 6.93,
-      "eval_loss": 0.276467502117157,
-      "eval_runtime": 393.6733,
-      "eval_samples_per_second": 10.915,
-      "eval_steps_per_second": 0.343,
-      "eval_wer": 0.16425075594625768,
-      "step": 13000
-    },
-    {
-      "epoch": 7.19,
-      "learning_rate": 3.299429935685051e-05,
-      "loss": 1.1326,
-      "step": 13500
-    },
-    {
-      "epoch": 7.19,
-      "eval_loss": 0.27056241035461426,
-      "eval_runtime": 391.6082,
-      "eval_samples_per_second": 10.973,
-      "eval_steps_per_second": 0.345,
-      "eval_wer": 0.1668277273813606,
-      "step": 13500
-    },
-    {
-      "epoch": 7.46,
-      "learning_rate": 3.116717014227246e-05,
-      "loss": 1.1342,
-      "step": 14000
-    },
-    {
-      "epoch": 7.46,
-      "eval_loss": 0.26654428243637085,
-      "eval_runtime": 388.567,
-      "eval_samples_per_second": 11.059,
-      "eval_steps_per_second": 0.347,
-      "eval_wer": 0.1638247243783576,
-      "step": 14000
-    },
-    {
-      "epoch": 7.72,
-      "learning_rate": 2.9340040927694404e-05,
-      "loss": 1.1286,
-      "step": 14500
-    },
-    {
-      "epoch": 7.72,
-      "eval_loss": 0.2668865919113159,
-      "eval_runtime": 384.4478,
-      "eval_samples_per_second": 11.177,
-      "eval_steps_per_second": 0.351,
-      "eval_wer": 0.1635857310597795,
-      "step": 14500
-    },
-    {
-      "epoch": 7.99,
-      "learning_rate": 2.7516565971545504e-05,
-      "loss": 1.1243,
-      "step": 15000
-    },
-    {
-      "epoch": 7.99,
-      "eval_loss": 0.2619013488292694,
-      "eval_runtime": 392.1143,
-      "eval_samples_per_second": 10.959,
-      "eval_steps_per_second": 0.344,
-      "eval_wer": 0.16234920041148415,
-      "step": 15000
-    },
-    {
-      "epoch": 8.26,
-      "learning_rate": 2.5689436756967453e-05,
-      "loss": 1.1173,
-      "step": 15500
-    },
-    {
-      "epoch": 8.26,
-      "eval_loss": 0.2651631236076355,
-      "eval_runtime": 388.7223,
-      "eval_samples_per_second": 11.054,
-      "eval_steps_per_second": 0.347,
-      "eval_wer": 0.16037490777975208,
-      "step": 15500
-    },
-    {
-      "epoch": 8.52,
-      "learning_rate": 2.3862307542389395e-05,
-      "loss": 1.1129,
-      "step": 16000
-    },
-    {
-      "epoch": 8.52,
-      "eval_loss": 0.26095372438430786,
-      "eval_runtime": 387.1141,
-      "eval_samples_per_second": 11.1,
-      "eval_steps_per_second": 0.349,
-      "eval_wer": 0.1597514469486788,
-      "step": 16000
-    },
-    {
-      "epoch": 8.79,
-      "learning_rate": 2.203517832781134e-05,
-      "loss": 1.1091,
-      "step": 16500
-    },
-    {
-      "epoch": 8.79,
-      "eval_loss": 0.2608127295970917,
-      "eval_runtime": 386.5271,
-      "eval_samples_per_second": 11.117,
-      "eval_steps_per_second": 0.349,
-      "eval_wer": 0.15837983312031756,
-      "step": 16500
-    },
-    {
-      "epoch": 9.06,
-      "learning_rate": 2.0208049113233286e-05,
-      "loss": 1.1053,
-      "step": 17000
-    },
-    {
-      "epoch": 9.06,
-      "eval_loss": 0.2632738947868347,
-      "eval_runtime": 389.2784,
-      "eval_samples_per_second": 11.038,
-      "eval_steps_per_second": 0.347,
-      "eval_wer": 0.1664016958134605,
-      "step": 17000
-    },
-    {
-      "epoch": 9.32,
-      "learning_rate": 1.8384574157084387e-05,
-      "loss": 1.1004,
-      "step": 17500
-    },
-    {
-      "epoch": 9.32,
-      "eval_loss": 0.2594461441040039,
-      "eval_runtime": 388.9349,
-      "eval_samples_per_second": 11.048,
-      "eval_steps_per_second": 0.347,
-      "eval_wer": 0.16618348452258486,
-      "step": 17500
-    },
-    {
-      "epoch": 9.59,
-      "learning_rate": 1.6557444942506332e-05,
-      "loss": 1.0995,
-      "step": 18000
-    },
-    {
-      "epoch": 9.59,
-      "eval_loss": 0.26234543323516846,
-      "eval_runtime": 383.4387,
-      "eval_samples_per_second": 11.206,
-      "eval_steps_per_second": 0.352,
-      "eval_wer": 0.15694587320884898,
-      "step": 18000
-    },
-    {
-      "epoch": 9.86,
-      "learning_rate": 1.4730315727928276e-05,
-      "loss": 1.0964,
-      "step": 18500
-    },
-    {
-      "epoch": 9.86,
-      "eval_loss": 0.26244357228279114,
-      "eval_runtime": 384.9493,
-      "eval_samples_per_second": 11.163,
-      "eval_steps_per_second": 0.351,
-      "eval_wer": 0.15968910086557145,
-      "step": 18500
-    },
-    {
-      "epoch": 10.12,
-      "learning_rate": 1.2903186513350224e-05,
-      "loss": 1.09,
-      "step": 19000
-    },
-    {
-      "epoch": 10.12,
-      "eval_loss": 0.2576591968536377,
-      "eval_runtime": 391.5397,
-      "eval_samples_per_second": 10.975,
-      "eval_steps_per_second": 0.345,
-      "eval_wer": 0.15782910938620281,
-      "step": 19000
-    },
-    {
-      "epoch": 10.39,
-      "learning_rate": 1.108336581563048e-05,
-      "loss": 1.089,
-      "step": 19500
-    },
-    {
-      "epoch": 10.39,
-      "eval_loss": 0.25744903087615967,
-      "eval_runtime": 384.7348,
-      "eval_samples_per_second": 11.169,
-      "eval_steps_per_second": 0.351,
-      "eval_wer": 0.1531219801115995,
-      "step": 19500
-    },
-    {
-      "epoch": 10.66,
-      "learning_rate": 9.256236601052426e-06,
-      "loss": 1.0864,
-      "step": 20000
-    },
-    {
-      "epoch": 10.66,
-      "eval_loss": 0.2556162476539612,
-      "eval_runtime": 391.8515,
-      "eval_samples_per_second": 10.966,
-      "eval_steps_per_second": 0.345,
-      "eval_wer": 0.15464945914772904,
-      "step": 20000
-    },
-    {
-      "epoch": 10.92,
-      "learning_rate": 7.429107386474371e-06,
-      "loss": 1.0806,
-      "step": 20500
-    },
-    {
-      "epoch": 10.92,
-      "eval_loss": 0.2548317313194275,
-      "eval_runtime": 384.3272,
-      "eval_samples_per_second": 11.181,
-      "eval_steps_per_second": 0.351,
-      "eval_wer": 0.1583174870372102,
-      "step": 20500
-    },
-    {
-      "epoch": 11.19,
-      "learning_rate": 5.6019781718963155e-06,
-      "loss": 1.0842,
-      "step": 21000
-    },
-    {
-      "epoch": 11.19,
-      "eval_loss": 0.25501224398612976,
-      "eval_runtime": 383.8764,
-      "eval_samples_per_second": 11.194,
-      "eval_steps_per_second": 0.352,
-      "eval_wer": 0.1542026455521265,
-      "step": 21000
-    },
-    {
-      "epoch": 11.45,
-      "learning_rate": 3.774848957318261e-06,
-      "loss": 1.0805,
-      "step": 21500
-    },
-    {
-      "epoch": 11.45,
-      "eval_loss": 0.25607678294181824,
-      "eval_runtime": 388.7678,
-      "eval_samples_per_second": 11.053,
-      "eval_steps_per_second": 0.347,
-      "eval_wer": 0.15236343610046033,
-      "step": 21500
-    },
-    {
-      "epoch": 11.72,
-      "learning_rate": 1.9477197427402063e-06,
-      "loss": 1.0722,
-      "step": 22000
-    },
-    {
-      "epoch": 11.72,
-      "eval_loss": 0.25402259826660156,
-      "eval_runtime": 385.5053,
-      "eval_samples_per_second": 11.146,
-      "eval_steps_per_second": 0.35,
-      "eval_wer": 0.1565614056963538,
-      "step": 22000
-    },
-    {
-      "epoch": 11.99,
-      "learning_rate": 1.2059052816215163e-07,
-      "loss": 1.0763,
-      "step": 22500
-    },
-    {
-      "epoch": 11.99,
-      "eval_loss": 0.2549177408218384,
-      "eval_runtime": 379.953,
-      "eval_samples_per_second": 11.309,
-      "eval_steps_per_second": 0.355,
-      "eval_wer": 0.15720564855512953,
-      "step": 22500
-    },
-    {
-      "epoch": 12.0,
-      "step": 22524,
-      "total_flos": 6.281601139352125e+20,
-      "train_loss": 0.5676147035501541,
-      "train_runtime": 172546.67,
-      "train_samples_per_second": 16.714,
-      "train_steps_per_second": 0.131
-    }
-  ],
-  "max_steps": 22524,
-  "num_train_epochs": 12,
-  "total_flos": 6.281601139352125e+20,
-  "trial_name": null,
-  "trial_params": null
-}

.ipynb_checkpoints/vocab-checkpoint.json

@@ -1 +0,0 @@
-{"#": 1, "'": 2, "-": 3, "a": 4, "b": 5, "c": 6, "d": 7, "e": 8, "f": 9, "g": 10, "h": 11, "i": 12, "j": 13, "k": 14, "l": 15, "m": 16, "n": 17, "o": 18, "p": 19, "q": 20, "r": 21, "s": 22, "t": 23, "u": 24, "v": 25, "w": 26, "x": 27, "y": 28, "z": 29, "·": 30, "à": 31, "ç": 32, "è": 33, "é": 34, "í": 35, "ï": 36, "ò": 37, "ó": 38, "ú": 39, "ü": 40, "ः": 41, "|": 0, "[UNK]": 42, "[PAD]": 43}

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}, {"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}]}