End of training

README.md

@@ -1,33 +1,33 @@
 ---
+library_name: transformers
+license: cc-by-nc-4.0
 base_model: facebook/mms-1b-all
+tags:
+- generated_from_trainer
 datasets:
 - common_voice_17_0
-library_name: transformers
-license: cc-by-nc-4.0
 metrics:
 - wer
 - bleu
-tags:
-- generated_from_trainer
 model-index:
 - name: wav2vec2-mms-1b-CV17.0
   results:
   - task:
-      type: automatic-speech-recognition
       name: Automatic Speech Recognition
+      type: automatic-speech-recognition
     dataset:
       name: common_voice_17_0
       type: common_voice_17_0
-      config: te
-      split: test
-      args: te
+      config: ta
+      split: test[:5%]+test[20%:25%]+test[60%:65%]+test[90%:]
+      args: ta
     metrics:
-    - type: wer
-      value: 1.2142857142857142
-      name: Wer
-    - type: bleu
-      value: 0.0
-      name: Bleu
+    - name: Wer
+      type: wer
+      value: 0.39458150446496143
+    - name: Bleu
+      type: bleu
+      value: 0.3894086227361947
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -37,10 +37,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [facebook/mms-1b-all](https://huggingface.co/facebook/mms-1b-all) on the common_voice_17_0 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 11.1713
-- Wer: 1.2143
-- Cer: 0.8147
-- Bleu: 0.0
+- Loss: 0.2560
+- Wer: 0.3946
+- Cer: 0.0667
+- Bleu: 0.3894
 
 ## Model description
 
@@ -59,7 +59,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.001
+- learning_rate: 0.0001
 - train_batch_size: 16
 - eval_batch_size: 8
 - seed: 42
@@ -68,18 +68,23 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.15
-- training_steps: 1000
+- training_steps: 5000
 - mixed_precision_training: Native AMP
 
 ### Training results
 
-| Training Loss | Epoch    | Step | Validation Loss | Wer    | Cer    | Bleu |
-|:-------------:|:--------:|:----:|:---------------:|:------:|:------:|:----:|
-| 7.86          | 57.1429  | 200  | 6.2814          | 1.0440 | 0.8624 | 0.0  |
-| 2.3343        | 114.2857 | 400  | 7.7524          | 1.0769 | 0.7876 | 0.0  |
-| 1.4057        | 171.4286 | 600  | 9.7458          | 1.1319 | 0.7940 | 0.0  |
-| 0.9348        | 228.5714 | 800  | 10.7001         | 1.1319 | 0.8090 | 0.0  |
-| 0.7253        | 285.7143 | 1000 | 11.1713         | 1.2143 | 0.8147 | 0.0  |
+| Training Loss | Epoch  | Step | Validation Loss | Wer    | Cer    | Bleu   |
+|:-------------:|:------:|:----:|:---------------:|:------:|:------:|:------:|
+| 5.2362        | 0.3509 | 500  | 0.3039          | 0.4233 | 0.0716 | 0.3579 |
+| 0.2003        | 0.7018 | 1000 | 0.2726          | 0.4072 | 0.0694 | 0.3806 |
+| 0.1821        | 1.0526 | 1500 | 0.2632          | 0.3993 | 0.0677 | 0.3890 |
+| 0.1792        | 1.4035 | 2000 | 0.2602          | 0.4011 | 0.0677 | 0.3850 |
+| 0.1764        | 1.7544 | 2500 | 0.2572          | 0.3984 | 0.0674 | 0.3850 |
+| 0.1771        | 2.1053 | 3000 | 0.2570          | 0.3955 | 0.0672 | 0.3918 |
+| 0.1777        | 2.4561 | 3500 | 0.2562          | 0.3970 | 0.0670 | 0.3866 |
+| 0.1721        | 2.8070 | 4000 | 0.2547          | 0.3975 | 0.0669 | 0.3841 |
+| 0.177         | 3.1579 | 4500 | 0.2560          | 0.3949 | 0.0668 | 0.3910 |
+| 0.1765        | 3.5088 | 5000 | 0.2560          | 0.3946 | 0.0667 | 0.3894 |
 
 
 ### Framework versions

adapter.tam.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0caf35e6ed3d0e0b1cd2821063f3f7df1a5d910d77cb226e00d5a5fc6251d870
-size 8921516
+oid sha256:02cb96152f540e4d4868bff054cf1f4849b3afc5c59d16d572650fcbfc7ddc64
+size 8926640