End of training

README.md

@@ -1,14 +1,13 @@
 ---
-library_name: transformers
 language:
 - lv
 license: apache-2.0
-base_model: FelixK7/whisper-medium-lv-ver2
+base_model: openai/whisper-medium
 tags:
 - hf-asr-leaderboard
 - generated_from_trainer
 datasets:
-- mozilla-foundation/common_voice_16_0
+- mozilla-foundation/common_voice_17_0
 metrics:
 - wer
 model-index:
@@ -18,15 +17,15 @@ model-index:
       name: Automatic Speech Recognition
       type: automatic-speech-recognition
     dataset:
-      name: Common Voice 16.0
-      type: mozilla-foundation/common_voice_16_0
+      name: Common Voice 17.0
+      type: mozilla-foundation/common_voice_17_0
       config: lv
       split: None
       args: 'config: lv, split: test'
     metrics:
     - name: Wer
       type: wer
-      value: 19.39252336448598
+      value: 50.0
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -34,10 +33,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # Whisper medium LV - Felikss Kleins
 
-This model is a fine-tuned version of [FelixK7/whisper-medium-lv-ver2](https://huggingface.co/FelixK7/whisper-medium-lv-ver2) on the Common Voice 16.0 dataset.
+This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on the Common Voice 17.0 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2882
-- Wer: 19.3925
+- Loss: 0.9473
+- Wer: 50.0
 
 ## Model description
 
@@ -62,25 +61,22 @@ The following hyperparameters were used during training:
 - seed: 42
 - gradient_accumulation_steps: 2
 - total_train_batch_size: 64
-- optimizer: Use adamw_hf with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 500
-- training_steps: 10000
-- mixed_precision_training: Native AMP
+- training_steps: 500
 
 ### Training results
 
-| Training Loss | Epoch    | Step | Validation Loss | Wer     |
-|:-------------:|:--------:|:----:|:---------------:|:-------:|
-| No log        | 99.0002  | 200  | 0.1666          | 11.4486 |
-| 0.0028        | 199.0002 | 400  | 0.2083          | 13.5514 |
-| 0.0007        | 299.0002 | 600  | 0.2815          | 20.7944 |
-| 0.0008        | 399.0002 | 800  | 0.2882          | 19.3925 |
+| Training Loss | Epoch | Step | Validation Loss | Wer     |
+|:-------------:|:-----:|:----:|:---------------:|:-------:|
+| No log        | 399.0 | 200  | 0.9567          | 57.6923 |
+| 0.3396        | 799.0 | 400  | 0.9473          | 50.0    |
 
 
 ### Framework versions
 
-- Transformers 4.46.0.dev0
-- Pytorch 2.0.1
-- Datasets 3.0.1
-- Tokenizers 0.20.1
+- Transformers 4.40.0.dev0
+- Pytorch 2.3.0+cu121
+- Datasets 2.18.0
+- Tokenizers 0.15.2

generation_config.json

@@ -244,6 +244,6 @@
     "transcribe": 50359,
     "translate": 50358
   },
-  "transformers_version": "4.46.0.dev0",
+  "transformers_version": "4.40.0.dev0",
   "use_cache": false
 }

runs/Oct22_09-40-03_whisper-test/events.out.tfevents.1729579206.whisper-test.35341.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7056cbcbbc2106142b68ee84b7977f4b69c5de81bc0c029bb9a8c96855d4fc02
-size 7256
+oid sha256:2d671d84ecf3ba8992f5b33750455966c67e6d1ec6008bb94347f9006ae1cf09
+size 7821