Upload 13 files

README.md

@@ -1,8 +1,6 @@
 ---
 tags:
 - generated_from_trainer
-metrics:
-- wer
 model-index:
 - name: wav2vec2-large-asr-th-2
   results: []
@@ -15,9 +13,14 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model was trained from scratch on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2590
-- Wer: 0.4210
-- Cer: 0.1146
+- eval_loss: 0.1819
+- eval_wer: 0.3346
+- eval_cer: 0.0910
+- eval_runtime: 735.0436
+- eval_samples_per_second: 13.822
+- eval_steps_per_second: 1.728
+- epoch: 0.95
+- step: 4000
 
 ## Model description
 
@@ -36,7 +39,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.0002
+- learning_rate: 0.0001
 - train_batch_size: 16
 - eval_batch_size: 8
 - seed: 42
@@ -44,23 +47,13 @@ The following hyperparameters were used during training:
 - total_train_batch_size: 48
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- lr_scheduler_warmup_steps: 600
-- training_steps: 4000
+- lr_scheduler_warmup_steps: 500
+- training_steps: 5000
 - mixed_precision_training: Native AMP
 
-### Training results
-
-| Training Loss | Epoch | Step | Validation Loss | Wer    | Cer    |
-|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|
-| 0.6189        | 0.24  | 1000 | 0.3571          | 0.5060 | 0.1449 |
-| 0.5435        | 0.47  | 2000 | 0.3255          | 0.4712 | 0.1328 |
-| 0.5612        | 0.71  | 3000 | 0.2870          | 0.4464 | 0.1233 |
-| 0.6737        | 0.95  | 4000 | 0.2590          | 0.4210 | 0.1146 |
-
-
 ### Framework versions
 
-- Transformers 4.27.3
+- Transformers 4.27.4
 - Pytorch 1.13.1+cu116
-- Datasets 2.10.1
+- Datasets 2.11.0
 - Tokenizers 0.13.2

config.json

@@ -109,7 +109,7 @@
     1
   ],
   "torch_dtype": "float32",
-  "transformers_version": "4.27.3",
+  "transformers_version": "4.27.4",
   "use_weighted_layer_sum": false,
   "vocab_size": 72,
   "xvector_output_dim": 512

language_model/attrs.json

@@ -1 +1 @@
-{"alpha": 0.5, "beta": 1.5, "unk_score_offset": -10.0, "score_boundary": true}
+{"alpha": 0.7, "beta": 1.0, "unk_score_offset": -10.0, "score_boundary": true}

language_model/internet-crawled.4gram.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a3a50973877491ce00617514e77aafb859b9ae0e28ae6902e16da3cde5d0787
+size 3499191609

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3db9d140ed973d933448e83b4a3d7c72b7683b7a077f52c258594763abf2139
+oid sha256:330f08323ba2112b309cdecc88208920a6afdd21d8d4b8f0b1ea27fabd5868d3
 size 1262197037

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab1acd7b1adc89516ec5569b2e31e361d047913189de035bffe974d3c7e42c8a
+oid sha256:e7c0bd0bd8e70f57d6247470affb116af5391526153c4774fbf17cfec59c3770
 size 3643