update model card README.md
Browse files- README.md +60 -0
- fine-tune-whisper-non-streaming-id.ipynb +43 -4
README.md
ADDED
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
language:
|
3 |
+
- id
|
4 |
+
license: apache-2.0
|
5 |
+
tags:
|
6 |
+
- whisper-event
|
7 |
+
- generated_from_trainer
|
8 |
+
model-index:
|
9 |
+
- name: Whisper Medium ID - FLEURS-CV
|
10 |
+
results: []
|
11 |
+
---
|
12 |
+
|
13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
14 |
+
should probably proofread and complete it, then remove this comment. -->
|
15 |
+
|
16 |
+
# Whisper Medium ID - FLEURS-CV
|
17 |
+
|
18 |
+
This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on the None dataset.
|
19 |
+
It achieves the following results on the evaluation set:
|
20 |
+
- eval_loss: 0.2563
|
21 |
+
- eval_wer: 8.4690
|
22 |
+
- eval_runtime: 2961.9108
|
23 |
+
- eval_samples_per_second: 1.453
|
24 |
+
- eval_steps_per_second: 0.091
|
25 |
+
- epoch: 14.29
|
26 |
+
- step: 5000
|
27 |
+
|
28 |
+
## Model description
|
29 |
+
|
30 |
+
More information needed
|
31 |
+
|
32 |
+
## Intended uses & limitations
|
33 |
+
|
34 |
+
More information needed
|
35 |
+
|
36 |
+
## Training and evaluation data
|
37 |
+
|
38 |
+
More information needed
|
39 |
+
|
40 |
+
## Training procedure
|
41 |
+
|
42 |
+
### Training hyperparameters
|
43 |
+
|
44 |
+
The following hyperparameters were used during training:
|
45 |
+
- learning_rate: 1e-05
|
46 |
+
- train_batch_size: 32
|
47 |
+
- eval_batch_size: 16
|
48 |
+
- seed: 42
|
49 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
50 |
+
- lr_scheduler_type: linear
|
51 |
+
- lr_scheduler_warmup_steps: 500
|
52 |
+
- training_steps: 10000
|
53 |
+
- mixed_precision_training: Native AMP
|
54 |
+
|
55 |
+
### Framework versions
|
56 |
+
|
57 |
+
- Transformers 4.26.0.dev0
|
58 |
+
- Pytorch 1.13.1+cu117
|
59 |
+
- Datasets 2.7.1.dev0
|
60 |
+
- Tokenizers 0.13.2
|
fine-tune-whisper-non-streaming-id.ipynb
CHANGED
@@ -5972,7 +5972,7 @@
|
|
5972 |
},
|
5973 |
{
|
5974 |
"cell_type": "code",
|
5975 |
-
"execution_count":
|
5976 |
"id": "c704f91e-241b-48c9-b8e0-f0da396a9663",
|
5977 |
"metadata": {
|
5978 |
"id": "c704f91e-241b-48c9-b8e0-f0da396a9663"
|
@@ -5980,8 +5980,8 @@
|
|
5980 |
"outputs": [],
|
5981 |
"source": [
|
5982 |
"kwargs = {\n",
|
5983 |
-
"
|
5984 |
-
"
|
5985 |
" \"language\": \"id\",\n",
|
5986 |
" \"model_name\": \"Whisper Medium ID - FLEURS-CV\", # a 'pretty' name for your model\n",
|
5987 |
" \"finetuned_from\": \"openai/whisper-medium\",\n",
|
@@ -6007,7 +6007,46 @@
|
|
6007 |
"metadata": {
|
6008 |
"id": "d7030622-caf7-4039-939b-6195cdaa2585"
|
6009 |
},
|
6010 |
-
"outputs": [
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
6011 |
"source": [
|
6012 |
"trainer.push_to_hub(**kwargs)"
|
6013 |
]
|
|
|
5972 |
},
|
5973 |
{
|
5974 |
"cell_type": "code",
|
5975 |
+
"execution_count": 24,
|
5976 |
"id": "c704f91e-241b-48c9-b8e0-f0da396a9663",
|
5977 |
"metadata": {
|
5978 |
"id": "c704f91e-241b-48c9-b8e0-f0da396a9663"
|
|
|
5980 |
"outputs": [],
|
5981 |
"source": [
|
5982 |
"kwargs = {\n",
|
5983 |
+
"# \"dataset_tags\": [\"google/fleurs\", \"mozilla-foundation/common_voice_11_0\"],\n",
|
5984 |
+
"# \"dataset\": [\"FLEURS\", \"Common Voice 11.0\"], # a 'pretty' name for the training dataset\n",
|
5985 |
" \"language\": \"id\",\n",
|
5986 |
" \"model_name\": \"Whisper Medium ID - FLEURS-CV\", # a 'pretty' name for your model\n",
|
5987 |
" \"finetuned_from\": \"openai/whisper-medium\",\n",
|
|
|
6007 |
"metadata": {
|
6008 |
"id": "d7030622-caf7-4039-939b-6195cdaa2585"
|
6009 |
},
|
6010 |
+
"outputs": [
|
6011 |
+
{
|
6012 |
+
"name": "stderr",
|
6013 |
+
"output_type": "stream",
|
6014 |
+
"text": [
|
6015 |
+
"Saving model checkpoint to ./\n",
|
6016 |
+
"Configuration saved in ./config.json\n",
|
6017 |
+
"Model weights saved in ./pytorch_model.bin\n",
|
6018 |
+
"Feature extractor saved in ./preprocessor_config.json\n"
|
6019 |
+
]
|
6020 |
+
},
|
6021 |
+
{
|
6022 |
+
"data": {
|
6023 |
+
"application/vnd.jupyter.widget-view+json": {
|
6024 |
+
"model_id": "88c804e93e1844dd8eca6aea753e7ef8",
|
6025 |
+
"version_major": 2,
|
6026 |
+
"version_minor": 0
|
6027 |
+
},
|
6028 |
+
"text/plain": [
|
6029 |
+
"Upload file pytorch_model.bin: 0%| | 32.0k/2.85G [00:00<?, ?B/s]"
|
6030 |
+
]
|
6031 |
+
},
|
6032 |
+
"metadata": {},
|
6033 |
+
"output_type": "display_data"
|
6034 |
+
},
|
6035 |
+
{
|
6036 |
+
"data": {
|
6037 |
+
"application/vnd.jupyter.widget-view+json": {
|
6038 |
+
"model_id": "be47f0485aa74ae6aa86faa95a079369",
|
6039 |
+
"version_major": 2,
|
6040 |
+
"version_minor": 0
|
6041 |
+
},
|
6042 |
+
"text/plain": [
|
6043 |
+
"Upload file runs/Dec17_13-22-39_150-136-214-225/events.out.tfevents.1671283363.150-136-214-225.126569.0: 85%|…"
|
6044 |
+
]
|
6045 |
+
},
|
6046 |
+
"metadata": {},
|
6047 |
+
"output_type": "display_data"
|
6048 |
+
}
|
6049 |
+
],
|
6050 |
"source": [
|
6051 |
"trainer.push_to_hub(**kwargs)"
|
6052 |
]
|