wav2vec2-base-timit-demo-colab

README.md

@@ -14,9 +14,6 @@ should probably proofread and complete it, then remove this comment. -->
 # wav2vec2-base-timit-demo
 
 This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the None dataset.
-It achieves the following results on the evaluation set:
-- Loss: 0.6519
-- Cer: 0.1121
 
 ## Model description
 
@@ -46,21 +43,9 @@ The following hyperparameters were used during training:
 - lr_scheduler_warmup_steps: 1000
 - num_epochs: 50
 
-### Training results
-
-| Training Loss | Epoch | Step | Validation Loss | Cer    |
-|:-------------:|:-----:|:----:|:---------------:|:------:|
-| 3.1338        | 8.0   | 500  | 0.5833          | 0.1592 |
-| 0.4869        | 16.0  | 1000 | 0.3597          | 0.1123 |
-| 0.2752        | 24.0  | 1500 | 0.4215          | 0.1161 |
-| 0.1733        | 32.0  | 2000 | 0.5183          | 0.1120 |
-| 0.1187        | 40.0  | 2500 | 0.6195          | 0.1138 |
-| 0.0906        | 48.0  | 3000 | 0.6519          | 0.1121 |
-
-
 ### Framework versions
 
-- Transformers 4.33.2
-- Pytorch 2.0.1+cu118
-- Datasets 2.14.6.dev0
-- Tokenizers 0.13.3
+- Transformers 4.35.2
+- Pytorch 2.1.0+cu121
+- Datasets 2.16.2.dev0
+- Tokenizers 0.15.0

config.json

@@ -85,7 +85,7 @@
   "num_hidden_layers": 24,
   "num_negatives": 100,
   "output_hidden_size": 1024,
-  "pad_token_id": 27,
+  "pad_token_id": 33,
   "proj_codevector_dim": 768,
   "tdnn_dilation": [
     1,
@@ -109,8 +109,8 @@
     1
   ],
   "torch_dtype": "float32",
-  "transformers_version": "4.33.2",
+  "transformers_version": "4.35.2",
   "use_weighted_layer_sum": false,
-  "vocab_size": 28,
+  "vocab_size": 36,
   "xvector_output_dim": 512
 }

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab5eecd662d47c568bc1777d386916b62a5edd21c93cf87d2150219f503313ac
+size 1261955080

runs/Jan07_17-05-22_91ef61d3e278/events.out.tfevents.1704647259.91ef61d3e278.13590.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcc1626a6440fb1136f8600c379f2bc996bf4c45075589c93ccd71b6caedde24
+size 5878

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f973acfff9c062c462b5d50a766e456db23a2803cd3f4376d35cf4ec27b3a291
-size 4027
+oid sha256:67ac779b86b57fbceae3e7fca67e690e50151a4a6b99c7edcce0df1140a66f35
+size 4600