Training in progress, step 500

README.md

@@ -1,61 +0,0 @@
----
-license: apache-2.0
-tags:
-- generated_from_trainer
-datasets:
-- 10th_science_tamil_to_english
-model-index:
-- name: 10th_science_ta_to_eng
-  results: []
----
-
-<!-- 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. -->
-
-# 10th_science_ta_to_eng
-
-This model is a fine-tuned version of [openai/whisper-base](https://huggingface.co/openai/whisper-base) on the 10th_science_tamil_to_english dataset.
-It achieves the following results on the evaluation set:
-- eval_loss: 3.0929
-- eval_wer: 157.7166
-- eval_runtime: 270.5806
-- eval_samples_per_second: 1.434
-- eval_steps_per_second: 0.092
-- epoch: 13.0
-- step: 500
-
-## 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: 1e-05
-- train_batch_size: 32
-- eval_batch_size: 16
-- seed: 42
-- gradient_accumulation_steps: 2
-- total_train_batch_size: 64
-- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
-- lr_scheduler_type: linear
-- lr_scheduler_warmup_steps: 500
-- training_steps: 5000
-- mixed_precision_training: Native AMP
-
-### Framework versions
-
-- Transformers 4.27.0.dev0
-- Pytorch 1.13.1+cu116
-- Datasets 2.10.1.dev0
-- Tokenizers 0.13.2

config.json

@@ -2,6 +2,7 @@
   "_name_or_path": "openai/whisper-base",
   "activation_dropout": 0.0,
   "activation_function": "gelu",
+  "apply_spec_augment": false,
   "architectures": [
     "WhisperForConditionalGeneration"
   ],
@@ -26,6 +27,12 @@
   "forced_decoder_ids": null,
   "init_std": 0.02,
   "is_encoder_decoder": true,
+  "mask_feature_length": 10,
+  "mask_feature_min_masks": 0,
+  "mask_feature_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_min_masks": 2,
+  "mask_time_prob": 0.05,
   "max_length": 448,
   "max_source_positions": 1500,
   "max_target_positions": 448,

generation_config.json

@@ -14,10 +14,6 @@
     [
       2,
       50359
-    ],
-    [
-      3,
-      50363
     ]
   ],
   "is_multilingual": true,

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:471c5297a1958b192baf8715629a179ff2c8947d77a9884b3d0fc31696b194df
+oid sha256:3bc702d51c5eb4393d61ea4995a797b151c2df2abd21ceb7c0ebedb33e2e67f7
 size 290458721

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8e15b1c996d0782293e42318a6b0c157827671b3d9c3919bcad6caae8584ee2
+oid sha256:5fd04f7e3e430263127912a8b73d2f63b44c704889d7eed0a1b4c4eac9b87d3f
 size 3707