End of training

README.md

@@ -1,41 +1,26 @@
 ---
-base_model: facebook/wav2vec2-xls-r-300m
-datasets:
-- fleurs
 license: apache-2.0
-metrics:
-- wer
+base_model: facebook/wav2vec2-xls-r-300m
 tags:
 - generated_from_trainer
+metrics:
+- wer
 model-index:
 - name: wav2vec2_xls_r_300m_FLEURS_Shona_1hr_v2
-  results:
-  - task:
-      type: automatic-speech-recognition
-      name: Automatic Speech Recognition
-    dataset:
-      name: fleurs
-      type: fleurs
-      config: sn_zw
-      split: validation
-      args: sn_zw
-    metrics:
-    - type: wer
-      value: 1.0053404539385848
-      name: Wer
+  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. -->
 
-[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/asr-africa-research-team/ASR%20Africa/runs/lpwyt5dt)
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/asr-africa-research-team/ASR%20Africa/runs/y5c5xv2u)
 # wav2vec2_xls_r_300m_FLEURS_Shona_1hr_v2
 
-This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the fleurs dataset.
+This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 13.8202
-- Wer: 1.0053
-- Cer: 1.1685
+- Loss: 14.3032
+- Wer: 1.0
+- Cer: 1.4684
 
 ## Model description
 
@@ -68,22 +53,19 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Wer    | Cer    |
-|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|
-| No log        | 1.0   | 8    | 14.7278         | 6.4466 | 0.9887 |
-| No log        | 2.0   | 16   | 14.6617         | 4.4427 | 1.0038 |
-| No log        | 3.0   | 24   | 14.4940         | 1.2634 | 1.0645 |
-| No log        | 4.0   | 32   | 14.2380         | 1.0    | 1.1589 |
-| No log        | 5.0   | 40   | 13.8564         | 1.0    | 0.9520 |
-| No log        | 6.0   | 48   | 13.0486         | 1.0    | 0.9997 |
-| No log        | 7.0   | 56   | 11.5115         | 1.0    | 1.0    |
-| No log        | 8.0   | 64   | 9.2890          | 1.0    | 1.0    |
-| No log        | 9.0   | 72   | 7.5411          | 1.0    | 1.0    |
-| No log        | 10.0  | 80   | 6.4612          | 1.0    | 1.0    |
-| No log        | 11.0  | 88   | 5.5385          | 1.0    | 1.0    |
-| No log        | 12.0  | 96   | 4.9727          | 1.0    | 1.0    |
-| 10.6364       | 13.0  | 104  | 4.6466          | 1.0    | 1.0    |
-| 10.6364       | 14.0  | 112  | 4.3706          | 1.0    | 1.0    |
+| Training Loss | Epoch | Step | Validation Loss | Wer | Cer    |
+|:-------------:|:-----:|:----:|:---------------:|:---:|:------:|
+| No log        | 1.0   | 8    | 14.7171         | 1.0 | 1.5610 |
+| No log        | 2.0   | 16   | 14.6350         | 1.0 | 1.1264 |
+| No log        | 3.0   | 24   | 14.4119         | 1.0 | 0.9462 |
+| No log        | 4.0   | 32   | 14.0495         | 1.0 | 0.9597 |
+| No log        | 5.0   | 40   | 13.4414         | 1.0 | 1.0    |
+| No log        | 6.0   | 48   | 12.1367         | 1.0 | 1.0    |
+| No log        | 7.0   | 56   | 9.9086          | 1.0 | 1.0    |
+| No log        | 8.0   | 64   | 7.8373          | 1.0 | 1.0    |
+| No log        | 9.0   | 72   | 6.3719          | 1.0 | 1.0    |
+| No log        | 10.0  | 80   | 5.4638          | 1.0 | 1.0    |
+| No log        | 11.0  | 88   | 4.8611          | 1.0 | 1.0    |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5c79a488c3d8a4634af956eb0a16a679a6c00a43b25c6df090fb6242bcf2f8d
+oid sha256:3f8e629c18bee7033adeaeb8b42a3bd91462d9fb0d34ec0f07da742c3264990e
 size 1261938680