Model save

README.md

@@ -2,8 +2,6 @@
 license: apache-2.0
 base_model: facebook/wav2vec2-large-xlsr-53
 tags:
-- automatic-speech-recognition
-- DewiBrynJones/banc-trawsgrifiadau-bangor-clean-with-ccv
 - generated_from_trainer
 metrics:
 - wer
@@ -17,10 +15,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # wav2vec2-xlsr-53-ft-btb-ccv-cy
 
-This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the DEWIBRYNJONES/BANC-TRAWSGRIFIADAU-BANGOR-CLEAN-WITH-CCV - DEFAULT dataset.
+This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on an unknown dataset.
 It achieves the following results on the evaluation set:
 - Loss: inf
-- Wer: 0.3665
+- Wer: 1.0
 
 ## Model description
 
@@ -46,7 +44,7 @@ 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_steps: 500
-- training_steps: 2000
+- training_steps: 4000
 - mixed_precision_training: Native AMP
 
 ### Training results
@@ -54,15 +52,25 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch  | Step | Validation Loss | Wer    |
 |:-------------:|:------:|:----:|:---------------:|:------:|
 | No log        | 0.3086 | 200  | inf             | 1.0    |
-| No log        | 0.6173 | 400  | inf             | 0.9468 |
-| 3.8579        | 0.9259 | 600  | inf             | 0.6823 |
-| 3.8579        | 1.2346 | 800  | inf             | 0.5246 |
-| 0.7662        | 1.5432 | 1000 | inf             | 0.4560 |
-| 0.7662        | 1.8519 | 1200 | inf             | 0.4314 |
-| 0.7662        | 2.1605 | 1400 | inf             | 0.4371 |
-| 0.5916        | 2.4691 | 1600 | inf             | 0.3861 |
-| 0.5916        | 2.7778 | 1800 | inf             | 0.3649 |
-| 0.4977        | 3.0864 | 2000 | inf             | 0.3665 |
+| No log        | 0.6173 | 400  | inf             | 0.8139 |
+| 3.6854        | 0.9259 | 600  | inf             | 0.6043 |
+| 3.6854        | 1.2346 | 800  | inf             | 0.5034 |
+| 0.7236        | 1.5432 | 1000 | inf             | 0.4452 |
+| 0.7236        | 1.8519 | 1200 | inf             | 0.4585 |
+| 0.7236        | 2.1605 | 1400 | inf             | 0.4736 |
+| 0.6244        | 2.4691 | 1600 | inf             | 0.4446 |
+| 0.6244        | 2.7778 | 1800 | inf             | 0.4992 |
+| 0.8045        | 3.0864 | 2000 | inf             | 0.6993 |
+| 0.8045        | 3.3951 | 2200 | inf             | 0.9155 |
+| 0.8045        | 3.7037 | 2400 | inf             | 1.0    |
+| 2.3067        | 4.0123 | 2600 | inf             | 0.9986 |
+| 2.3067        | 4.3210 | 2800 | inf             | 1.0    |
+| 3.008         | 4.6296 | 3000 | inf             | 1.0    |
+| 3.008         | 4.9383 | 3200 | inf             | 1.0    |
+| 3.008         | 5.2469 | 3400 | inf             | 1.0    |
+| 3.032         | 5.5556 | 3600 | inf             | 1.0    |
+| 3.032         | 5.8642 | 3800 | inf             | 1.0    |
+| 3.0173        | 6.1728 | 4000 | inf             | 1.0    |
 
 
 ### Framework versions