Hugging Face's logo

csikasote
/
mms-zeroshot-300m-genbed-combined-model

Automatic Speech Recognition
Transformers
Safetensors
wav2vec2
genbed
mms
Generated from Trainer
Inference Endpoints
Model card Files Community
csikasote commited on
Commit
657ae2a
•
1 Parent(s): e660d3f

Model save

Browse files
Files changed (2) hide show
  1. README.md +90 -0
  2. model.safetensors +1 -1
README.md ADDED
@@ -0,0 +1,90 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: cc-by-nc-4.0
4
+ base_model: mms-meta/mms-zeroshot-300m
5
+ tags:
6
+ - generated_from_trainer
7
+ metrics:
8
+ - wer
9
+ model-index:
10
+ - name: mms-zeroshot-300m-genbed-combined-model
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ # mms-zeroshot-300m-genbed-combined-model
18
+
19
+ This model is a fine-tuned version of [mms-meta/mms-zeroshot-300m](https://huggingface.co/mms-meta/mms-zeroshot-300m) on an unknown dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 0.2803
22
+ - Wer: 0.4357
23
+
24
+ ## Model description
25
+
26
+ More information needed
27
+
28
+ ## Intended uses & limitations
29
+
30
+ More information needed
31
+
32
+ ## Training and evaluation data
33
+
34
+ More information needed
35
+
36
+ ## Training procedure
37
+
38
+ ### Training hyperparameters
39
+
40
+ The following hyperparameters were used during training:
41
+ - learning_rate: 0.0003
42
+ - train_batch_size: 8
43
+ - eval_batch_size: 8
44
+ - seed: 42
45
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
+ - lr_scheduler_type: linear
47
+ - lr_scheduler_warmup_steps: 100
48
+ - num_epochs: 30.0
49
+ - mixed_precision_training: Native AMP
50
+
51
+ ### Training results
52
+
53
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
54
+ |:-------------:|:------:|:----:|:---------------:|:------:|
55
+ | No log | 0.2747 | 200 | 2.2031 | 1.0 |
56
+ | No log | 0.5495 | 400 | 0.4235 | 0.6042 |
57
+ | 2.7468 | 0.8242 | 600 | 0.3791 | 0.5722 |
58
+ | 2.7468 | 1.0989 | 800 | 0.3588 | 0.5632 |
59
+ | 0.5446 | 1.3736 | 1000 | 0.3489 | 0.5446 |
60
+ | 0.5446 | 1.6484 | 1200 | 0.3406 | 0.5458 |
61
+ | 0.5446 | 1.9231 | 1400 | 0.3326 | 0.5183 |
62
+ | 0.4932 | 2.1978 | 1600 | 0.3235 | 0.5237 |
63
+ | 0.4932 | 2.4725 | 1800 | 0.3202 | 0.5058 |
64
+ | 0.4644 | 2.7473 | 2000 | 0.3204 | 0.504 |
65
+ | 0.4644 | 3.0220 | 2200 | 0.3144 | 0.4910 |
66
+ | 0.4644 | 3.2967 | 2400 | 0.3076 | 0.4957 |
67
+ | 0.4505 | 3.5714 | 2600 | 0.3039 | 0.4751 |
68
+ | 0.4505 | 3.8462 | 2800 | 0.3027 | 0.4785 |
69
+ | 0.433 | 4.1209 | 3000 | 0.3013 | 0.4682 |
70
+ | 0.433 | 4.3956 | 3200 | 0.2961 | 0.4765 |
71
+ | 0.433 | 4.6703 | 3400 | 0.2914 | 0.468 |
72
+ | 0.4203 | 4.9451 | 3600 | 0.2909 | 0.4656 |
73
+ | 0.4203 | 5.2198 | 3800 | 0.2946 | 0.4508 |
74
+ | 0.4042 | 5.4945 | 4000 | 0.2901 | 0.4434 |
75
+ | 0.4042 | 5.7692 | 4200 | 0.2900 | 0.4463 |
76
+ | 0.4042 | 6.0440 | 4400 | 0.2840 | 0.4449 |
77
+ | 0.3962 | 6.3187 | 4600 | 0.2820 | 0.4448 |
78
+ | 0.3962 | 6.5934 | 4800 | 0.2771 | 0.4326 |
79
+ | 0.3881 | 6.8681 | 5000 | 0.2768 | 0.4294 |
80
+ | 0.3881 | 7.1429 | 5200 | 0.2787 | 0.4385 |
81
+ | 0.3881 | 7.4176 | 5400 | 0.2795 | 0.4309 |
82
+ | 0.3784 | 7.6923 | 5600 | 0.2803 | 0.4357 |
83
+
84
+
85
+ ### Framework versions
86
+
87
+ - Transformers 4.46.0.dev0
88
+ - Pytorch 2.4.1+cu121
89
+ - Datasets 3.0.1
90
+ - Tokenizers 0.20.0
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d4fd25d5b818f3a817e5c6e29d663b7d2f5e956f30ae0b11dbb50efae1d9159a
3
  size 1265394748
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dcf9459b4f67ad8a0f5cc6bb051a8f4a972e376e5647fdd1375f525b512df898
3
  size 1265394748