gglabs/stt-turbo-multilingual-test
Browse files- README.md +67 -0
- adapter_config.json +39 -0
- adapter_model.safetensors +3 -0
- adapter_model/adapter_config.json +39 -0
- adapter_model/adapter_model.safetensors +3 -0
- preprocessor_config.json +14 -0
- runs/May02_11-03-41_gglabs-a6000/events.out.tfevents.1746151421.gglabs-a6000.804743.0 +3 -0
- runs/May02_11-09-34_gglabs-a6000/events.out.tfevents.1746151775.gglabs-a6000.807080.0 +3 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,67 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
language:
|
4 |
+
- multilingual
|
5 |
+
license: mit
|
6 |
+
base_model: openai/whisper-large-v3-turbo
|
7 |
+
tags:
|
8 |
+
- generated_from_trainer
|
9 |
+
metrics:
|
10 |
+
- wer
|
11 |
+
model-index:
|
12 |
+
- name: Whisper Turbo Multilingual (ko, ja, zh, en)
|
13 |
+
results: []
|
14 |
+
---
|
15 |
+
|
16 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
17 |
+
should probably proofread and complete it, then remove this comment. -->
|
18 |
+
|
19 |
+
# Whisper Turbo Multilingual (ko, ja, zh, en)
|
20 |
+
|
21 |
+
This model is a fine-tuned version of [openai/whisper-large-v3-turbo](https://huggingface.co/openai/whisper-large-v3-turbo) on the custom_multilingual dataset.
|
22 |
+
It achieves the following results on the evaluation set:
|
23 |
+
- Loss: 0.3817
|
24 |
+
- Wer: 25.9259
|
25 |
+
|
26 |
+
## Model description
|
27 |
+
|
28 |
+
More information needed
|
29 |
+
|
30 |
+
## Intended uses & limitations
|
31 |
+
|
32 |
+
More information needed
|
33 |
+
|
34 |
+
## Training and evaluation data
|
35 |
+
|
36 |
+
More information needed
|
37 |
+
|
38 |
+
## Training procedure
|
39 |
+
|
40 |
+
### Training hyperparameters
|
41 |
+
|
42 |
+
The following hyperparameters were used during training:
|
43 |
+
- learning_rate: 0.001
|
44 |
+
- train_batch_size: 4
|
45 |
+
- eval_batch_size: 4
|
46 |
+
- seed: 42
|
47 |
+
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
48 |
+
- lr_scheduler_type: linear
|
49 |
+
- lr_scheduler_warmup_steps: 5
|
50 |
+
- training_steps: 20
|
51 |
+
- mixed_precision_training: Native AMP
|
52 |
+
|
53 |
+
### Training results
|
54 |
+
|
55 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
56 |
+
|:-------------:|:------:|:----:|:---------------:|:-------:|
|
57 |
+
| 0.6954 | 0.1754 | 10 | 0.4175 | 32.7160 |
|
58 |
+
| 0.2358 | 0.3509 | 20 | 0.3817 | 25.9259 |
|
59 |
+
|
60 |
+
|
61 |
+
### Framework versions
|
62 |
+
|
63 |
+
- PEFT 0.15.2.dev0
|
64 |
+
- Transformers 4.46.3
|
65 |
+
- Pytorch 2.3.1+cu121
|
66 |
+
- Datasets 3.0.0
|
67 |
+
- Tokenizers 0.20.3
|
adapter_config.json
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": {
|
4 |
+
"base_model_class": "WhisperForConditionalGeneration",
|
5 |
+
"parent_library": "transformers.models.whisper.modeling_whisper"
|
6 |
+
},
|
7 |
+
"base_model_name_or_path": "openai/whisper-large-v3-turbo",
|
8 |
+
"bias": "none",
|
9 |
+
"corda_config": null,
|
10 |
+
"eva_config": null,
|
11 |
+
"exclude_modules": null,
|
12 |
+
"fan_in_fan_out": false,
|
13 |
+
"inference_mode": true,
|
14 |
+
"init_lora_weights": true,
|
15 |
+
"layer_replication": null,
|
16 |
+
"layers_pattern": null,
|
17 |
+
"layers_to_transform": null,
|
18 |
+
"loftq_config": {},
|
19 |
+
"lora_alpha": 64,
|
20 |
+
"lora_bias": false,
|
21 |
+
"lora_dropout": 0.05,
|
22 |
+
"megatron_config": null,
|
23 |
+
"megatron_core": "megatron.core",
|
24 |
+
"modules_to_save": null,
|
25 |
+
"peft_type": "LORA",
|
26 |
+
"r": 64,
|
27 |
+
"rank_pattern": {},
|
28 |
+
"revision": null,
|
29 |
+
"target_modules": [
|
30 |
+
"v_proj",
|
31 |
+
"k_proj",
|
32 |
+
"q_proj",
|
33 |
+
"o_proj"
|
34 |
+
],
|
35 |
+
"task_type": null,
|
36 |
+
"trainable_token_indices": null,
|
37 |
+
"use_dora": false,
|
38 |
+
"use_rslora": false
|
39 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:af1da2ff2cefc9b912cced6f36b19cdb9f3f024e238710c013c88146ae9cb926
|
3 |
+
size 78677456
|
adapter_model/adapter_config.json
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": {
|
4 |
+
"base_model_class": "WhisperForConditionalGeneration",
|
5 |
+
"parent_library": "transformers.models.whisper.modeling_whisper"
|
6 |
+
},
|
7 |
+
"base_model_name_or_path": "openai/whisper-large-v3-turbo",
|
8 |
+
"bias": "none",
|
9 |
+
"corda_config": null,
|
10 |
+
"eva_config": null,
|
11 |
+
"exclude_modules": null,
|
12 |
+
"fan_in_fan_out": false,
|
13 |
+
"inference_mode": true,
|
14 |
+
"init_lora_weights": true,
|
15 |
+
"layer_replication": null,
|
16 |
+
"layers_pattern": null,
|
17 |
+
"layers_to_transform": null,
|
18 |
+
"loftq_config": {},
|
19 |
+
"lora_alpha": 64,
|
20 |
+
"lora_bias": false,
|
21 |
+
"lora_dropout": 0.05,
|
22 |
+
"megatron_config": null,
|
23 |
+
"megatron_core": "megatron.core",
|
24 |
+
"modules_to_save": null,
|
25 |
+
"peft_type": "LORA",
|
26 |
+
"r": 64,
|
27 |
+
"rank_pattern": {},
|
28 |
+
"revision": null,
|
29 |
+
"target_modules": [
|
30 |
+
"v_proj",
|
31 |
+
"k_proj",
|
32 |
+
"q_proj",
|
33 |
+
"o_proj"
|
34 |
+
],
|
35 |
+
"task_type": null,
|
36 |
+
"trainable_token_indices": null,
|
37 |
+
"use_dora": false,
|
38 |
+
"use_rslora": false
|
39 |
+
}
|
adapter_model/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:edb48c5e98da53d065059f7dde6c38c2a815117f26f14ab700203f42fd0aef0d
|
3 |
+
size 78677456
|
preprocessor_config.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"chunk_length": 30,
|
3 |
+
"feature_extractor_type": "WhisperFeatureExtractor",
|
4 |
+
"feature_size": 128,
|
5 |
+
"hop_length": 160,
|
6 |
+
"n_fft": 400,
|
7 |
+
"n_samples": 480000,
|
8 |
+
"nb_max_frames": 3000,
|
9 |
+
"padding_side": "right",
|
10 |
+
"padding_value": 0.0,
|
11 |
+
"processor_class": "WhisperProcessor",
|
12 |
+
"return_attention_mask": false,
|
13 |
+
"sampling_rate": 16000
|
14 |
+
}
|
runs/May02_11-03-41_gglabs-a6000/events.out.tfevents.1746151421.gglabs-a6000.804743.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a031d286ddf67368ec94e5e91868c084297444a17b062a785a48994169b714d2
|
3 |
+
size 9420
|
runs/May02_11-09-34_gglabs-a6000/events.out.tfevents.1746151775.gglabs-a6000.807080.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e2a7d2d6c7b660c5cfe43611ee24849261a5c5c4d3b9ee06e0a2a8b5021b6b42
|
3 |
+
size 6726
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:41fb0e3f8d67f81379987022f36a35e88e1a6d30d77e9d672d9d599fcd9b8cb3
|
3 |
+
size 5496
|