thirty_wav2vec2_ft_960h_no_lm

README.md

@@ -15,11 +15,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 # 960h
 
-This model is a fine-tuned version of [facebook/wav2vec2-base-960h](https://huggingface.co/facebook/wav2vec2-base-960h) on the None dataset.
+This model is a fine-tuned version of [facebook/wav2vec2-base-960h](https://huggingface.co/facebook/wav2vec2-base-960h) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.2440
-- Wer: 40.5592
-- Cer: 21.2837
+- Loss: 0.5325
+- Wer: 24.4442
+- Cer: 12.0113
 
 ## Model description
 
@@ -45,17 +45,17 @@ 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: 2000
-- num_epochs: 50
+- training_steps: 2700
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Wer     | Cer     |
 |:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|
-| 6.4178        | 9.26  | 500  | 3.0304          | 100.0   | 99.0785 |
-| 3.418         | 18.52 | 1000 | 2.9473          | 100.0   | 99.0785 |
-| 2.3895        | 27.78 | 1500 | 1.1051          | 47.8959 | 24.0394 |
-| 0.8914        | 37.04 | 2000 | 1.2159          | 43.2724 | 22.3298 |
-| 0.5237        | 46.3  | 2500 | 1.2440          | 40.5592 | 21.2837 |
+| 1.0759        | 1.75  | 500  | 0.7781          | 32.9761 | 16.6493 |
+| 0.8049        | 3.51  | 1000 | 0.6552          | 29.8584 | 14.9333 |
+| 0.7047        | 5.26  | 1500 | 0.6050          | 27.5232 | 13.6151 |
+| 0.6339        | 7.02  | 2000 | 0.5865          | 26.3889 | 13.1279 |
+| 0.5331        | 8.77  | 2500 | 0.5325          | 24.4442 | 12.0113 |
 
 
 ### Framework versions

config.json

@@ -46,7 +46,6 @@
   "ctc_zero_infinity": false,
   "diversity_loss_weight": 0.1,
   "do_stable_layer_norm": false,
-  "dropout": 0.2,
   "eos_token_id": 2,
   "feat_extract_activation": "gelu",
   "feat_extract_dropout": 0.0,
@@ -80,7 +79,7 @@
   "num_hidden_layers": 12,
   "num_negatives": 100,
   "output_hidden_size": 768,
-  "pad_token_id": 29,
+  "pad_token_id": 0,
   "proj_codevector_dim": 256,
   "tdnn_dilation": [
     1,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5029fdeb581adcea5ec74b2f9910d8cee2fcebf811370b61c33549dede02bab
+oid sha256:07f386037321e42c35e56cc1a6297492bc34f2132087370d35c19578a0f7ba11
 size 377611072

runs/Apr12_21-51-44_nfcbsu9pri/events.out.tfevents.1712959407.nfcbsu9pri.32.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:364bf2a2794d323aea64215a163d4538a0c5d3a34f4277add5f14b99cae4a518
+size 9305

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cfb5c0eb77e58041b909c67ec1b153af12cc6bf49d7a2441bf62a403ef22f9e2
+oid sha256:45fc5858186fda138bced49e325683ff1c6a71f47398af284e78caeff0db6a4d
 size 4527