Update README.md

README.md

@@ -4,13 +4,13 @@ language:
 license: apache-2.0
 tags:
 - automatic-speech-recognition
-- mozilla-foundation/common_voice_7_0
+- mozilla-foundation/common_voice_8_0
 - generated_from_trainer
 - hu
 - robust-speech-event
 - model_for_talk
 datasets:
-- mozilla-foundation/common_voice_7_0
+- mozilla-foundation/common_voice_8_0
 
 model-index:
 - name: Akashpb13/xlsr_hungarian_new
@@ -19,16 +19,16 @@ model-index:
       name: Automatic Speech Recognition 
       type: automatic-speech-recognition
     dataset:
-      name: Common Voice 7
-      type: mozilla-foundation/common_voice_7_0
+      name: Common Voice 8
+      type: mozilla-foundation/common_voice_8_0
       args: hu
     metrics:
        - name: Test WER
          type: wer
-         value: 0.02698525418772714
+         value: 0.2851621517163838
        - name: Test CER
          type: cer
-         value: 0.005033063261641211
+         value: 0.06112982522287432
   - task: 
       name: Automatic Speech Recognition
       type: automatic-speech-recognition
@@ -39,18 +39,18 @@ model-index:
     metrics:
        - name: Test WER
          type: wer
-         value: 0.02698525418772714
+         value: 0.2851621517163838
        - name: Test CER
          type: cer
-         value: 0.005033063261641211
+         value: 0.06112982522287432
 ---
 
 # Akashpb13/xlsr_hungarian_new
 
 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_7_0 - hu dataset.
-It achieves the following results on evaluation set (which is 10 percent of train data set merged with invalidated data, reported, other, dev and validated datasets):
-- Loss: 0.184265
-- Wer: 0.292771
+It achieves the following results on evaluation set (which is 10 percent of train data set merged with invalidated data, reported, other and dev datasets):
+- Loss: 0.197464
+- Wer: 0.330094
 ## Model description
 "facebook/wav2vec2-xls-r-300m" was finetuned.
 
@@ -73,8 +73,6 @@ The following hyperparameters were used during training:
 - eval_batch_size: 16
 - seed: 13
 - gradient_accumulation_steps: 16
-- total_train_batch_size: 316
-- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine_with_restarts
 - lr_scheduler_warmup_steps: 500
 - num_epochs: 100
@@ -83,19 +81,14 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-Step | Training Loss | Validation Loss | Wer      
-------|---------------|-----------------|----------
- 500  | 4.825900      | 1.001413        | 0.810308 
- 1000 | 0.561400      | 0.202275        | 0.361987 
- 1500 | 0.298900      | 0.169643        | 0.326449 
- 2000 | 0.236500      | 0.168602        | 0.316215 
- 2500 | 0.199100      | 0.182484        | 0.308587 
- 3000 | 0.179100      | 0.178076        | 0.303005 
- 3500 | 0.161500      | 0.179107        | 0.299935 
- 4000 | 0.151700      | 0.183371        | 0.295283 
- 4500 | 0.143700      | 0.184443        | 0.295283 
- 5000 | 0.138900      | 0.184265        | 0.292771     
-
+| Step | Training Loss | Validation Loss | Wer      |
+|------|---------------|-----------------|----------|
+| 500  | 4.785300      | 0.952295        | 0.796236 |
+| 1000 | 0.535800      | 0.217474        | 0.381613 |
+| 1500 | 0.258400      | 0.205524        | 0.345056 |
+| 2000 | 0.202800      | 0.198680        | 0.336264 |
+| 2500 | 0.182700      | 0.197464        | 0.330094 |
+     
 
 ### Framework versions
 - Transformers 4.16.0.dev0
@@ -105,9 +98,9 @@ Step | Training Loss | Validation Loss | Wer
 
 #### Evaluation Commands
 
-1. To evaluate on `mozilla-foundation/common_voice_7_0` with split `test`
+1. To evaluate on `mozilla-foundation/common_voice_8_0` with split `test`
 
 ```bash
-python eval.py --model_id Akashpb13/xlsr_hungarian_new --dataset mozilla-foundation/common_voice_7_0 --config hu --split test
+python eval.py --model_id Akashpb13/xlsr_hungarian_new --dataset mozilla-foundation/common_voice_8_0 --config hu --split test
 ```