Instructions to use vtlustos/whisper-large-v2_lora_int8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use vtlustos/whisper-large-v2_lora_int8 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="vtlustos/whisper-large-v2_lora_int8")# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("vtlustos/whisper-large-v2_lora_int8") model = AutoModelForSpeechSeq2Seq.from_pretrained("vtlustos/whisper-large-v2_lora_int8", device_map="auto") - Notebooks
- Google Colab
- Kaggle
End of training
Browse files- .gitignore +1 -0
- adapter_config.json +18 -0
- adapter_model.bin +3 -0
- config.json +64 -0
- generation_config.json +117 -0
- preprocessor_config.json +14 -0
- pytorch_model.bin +3 -0
- runs/May12_11-49-28_galdor3.metacentrum.cz/1683884974.661549/events.out.tfevents.1683884974.galdor3.metacentrum.cz.887203.1 +3 -0
- runs/May12_11-49-28_galdor3.metacentrum.cz/events.out.tfevents.1683884974.galdor3.metacentrum.cz.887203.0 +3 -0
- runs/May12_11-51-14_galdor3.metacentrum.cz/1683885078.3930595/events.out.tfevents.1683885078.galdor3.metacentrum.cz.888975.1 +3 -0
- runs/May12_11-51-14_galdor3.metacentrum.cz/events.out.tfevents.1683885078.galdor3.metacentrum.cz.888975.0 +3 -0
- runs/May12_11-52-47_galdor3.metacentrum.cz/1683885171.1735933/events.out.tfevents.1683885171.galdor3.metacentrum.cz.891624.1 +3 -0
- runs/May12_11-52-47_galdor3.metacentrum.cz/events.out.tfevents.1683885171.galdor3.metacentrum.cz.891624.0 +3 -0
- training_args.bin +3 -0
.gitignore
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
checkpoint-*/
|
adapter_config.json
ADDED
|
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"base_model_name_or_path": "openai/whisper-large-v2",
|
| 3 |
+
"bias": "none",
|
| 4 |
+
"enable_lora": null,
|
| 5 |
+
"fan_in_fan_out": false,
|
| 6 |
+
"inference_mode": true,
|
| 7 |
+
"lora_alpha": 16,
|
| 8 |
+
"lora_dropout": 0.05,
|
| 9 |
+
"merge_weights": false,
|
| 10 |
+
"modules_to_save": null,
|
| 11 |
+
"peft_type": "LORA",
|
| 12 |
+
"r": 16,
|
| 13 |
+
"target_modules": [
|
| 14 |
+
"q_proj",
|
| 15 |
+
"v_proj"
|
| 16 |
+
],
|
| 17 |
+
"task_type": null
|
| 18 |
+
}
|
adapter_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8ccae3e99cbf37991db216176b431ada1e9d962a207fb761d4ddbc5b5a97680c
|
| 3 |
+
size 31598989
|
config.json
ADDED
|
@@ -0,0 +1,64 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "openai/whisper-large-v2",
|
| 3 |
+
"activation_dropout": 0.0,
|
| 4 |
+
"activation_function": "gelu",
|
| 5 |
+
"apply_spec_augment": false,
|
| 6 |
+
"architectures": [
|
| 7 |
+
"WhisperForConditionalGeneration"
|
| 8 |
+
],
|
| 9 |
+
"attention_dropout": 0.0,
|
| 10 |
+
"begin_suppress_tokens": [
|
| 11 |
+
220,
|
| 12 |
+
50257
|
| 13 |
+
],
|
| 14 |
+
"bos_token_id": 50257,
|
| 15 |
+
"classifier_proj_size": 256,
|
| 16 |
+
"d_model": 1280,
|
| 17 |
+
"decoder_attention_heads": 20,
|
| 18 |
+
"decoder_ffn_dim": 5120,
|
| 19 |
+
"decoder_layerdrop": 0.0,
|
| 20 |
+
"decoder_layers": 32,
|
| 21 |
+
"decoder_start_token_id": 50258,
|
| 22 |
+
"dropout": 0.0,
|
| 23 |
+
"encoder_attention_heads": 20,
|
| 24 |
+
"encoder_ffn_dim": 5120,
|
| 25 |
+
"encoder_layerdrop": 0.0,
|
| 26 |
+
"encoder_layers": 32,
|
| 27 |
+
"eos_token_id": 50257,
|
| 28 |
+
"forced_decoder_ids": [
|
| 29 |
+
[
|
| 30 |
+
1,
|
| 31 |
+
50283
|
| 32 |
+
],
|
| 33 |
+
[
|
| 34 |
+
2,
|
| 35 |
+
50359
|
| 36 |
+
],
|
| 37 |
+
[
|
| 38 |
+
3,
|
| 39 |
+
50363
|
| 40 |
+
]
|
| 41 |
+
],
|
| 42 |
+
"init_std": 0.02,
|
| 43 |
+
"is_encoder_decoder": true,
|
| 44 |
+
"mask_feature_length": 10,
|
| 45 |
+
"mask_feature_min_masks": 0,
|
| 46 |
+
"mask_feature_prob": 0.0,
|
| 47 |
+
"mask_time_length": 10,
|
| 48 |
+
"mask_time_min_masks": 2,
|
| 49 |
+
"mask_time_prob": 0.05,
|
| 50 |
+
"max_length": 448,
|
| 51 |
+
"max_source_positions": 1500,
|
| 52 |
+
"max_target_positions": 448,
|
| 53 |
+
"model_type": "whisper",
|
| 54 |
+
"num_hidden_layers": 32,
|
| 55 |
+
"num_mel_bins": 80,
|
| 56 |
+
"pad_token_id": 50257,
|
| 57 |
+
"scale_embedding": false,
|
| 58 |
+
"suppress_tokens": [],
|
| 59 |
+
"torch_dtype": "float16",
|
| 60 |
+
"transformers_version": "4.27.4",
|
| 61 |
+
"use_cache": true,
|
| 62 |
+
"use_weighted_layer_sum": false,
|
| 63 |
+
"vocab_size": 51865
|
| 64 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,117 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"begin_suppress_tokens": [
|
| 4 |
+
220,
|
| 5 |
+
50257
|
| 6 |
+
],
|
| 7 |
+
"bos_token_id": 50257,
|
| 8 |
+
"decoder_start_token_id": 50258,
|
| 9 |
+
"eos_token_id": 50257,
|
| 10 |
+
"forced_decoder_ids": [
|
| 11 |
+
[
|
| 12 |
+
1,
|
| 13 |
+
50259
|
| 14 |
+
],
|
| 15 |
+
[
|
| 16 |
+
2,
|
| 17 |
+
50359
|
| 18 |
+
],
|
| 19 |
+
[
|
| 20 |
+
3,
|
| 21 |
+
50363
|
| 22 |
+
]
|
| 23 |
+
],
|
| 24 |
+
"max_length": 448,
|
| 25 |
+
"pad_token_id": 50257,
|
| 26 |
+
"suppress_tokens": [
|
| 27 |
+
1,
|
| 28 |
+
2,
|
| 29 |
+
7,
|
| 30 |
+
8,
|
| 31 |
+
9,
|
| 32 |
+
10,
|
| 33 |
+
14,
|
| 34 |
+
25,
|
| 35 |
+
26,
|
| 36 |
+
27,
|
| 37 |
+
28,
|
| 38 |
+
29,
|
| 39 |
+
31,
|
| 40 |
+
58,
|
| 41 |
+
59,
|
| 42 |
+
60,
|
| 43 |
+
61,
|
| 44 |
+
62,
|
| 45 |
+
63,
|
| 46 |
+
90,
|
| 47 |
+
91,
|
| 48 |
+
92,
|
| 49 |
+
93,
|
| 50 |
+
359,
|
| 51 |
+
503,
|
| 52 |
+
522,
|
| 53 |
+
542,
|
| 54 |
+
873,
|
| 55 |
+
893,
|
| 56 |
+
902,
|
| 57 |
+
918,
|
| 58 |
+
922,
|
| 59 |
+
931,
|
| 60 |
+
1350,
|
| 61 |
+
1853,
|
| 62 |
+
1982,
|
| 63 |
+
2460,
|
| 64 |
+
2627,
|
| 65 |
+
3246,
|
| 66 |
+
3253,
|
| 67 |
+
3268,
|
| 68 |
+
3536,
|
| 69 |
+
3846,
|
| 70 |
+
3961,
|
| 71 |
+
4183,
|
| 72 |
+
4667,
|
| 73 |
+
6585,
|
| 74 |
+
6647,
|
| 75 |
+
7273,
|
| 76 |
+
9061,
|
| 77 |
+
9383,
|
| 78 |
+
10428,
|
| 79 |
+
10929,
|
| 80 |
+
11938,
|
| 81 |
+
12033,
|
| 82 |
+
12331,
|
| 83 |
+
12562,
|
| 84 |
+
13793,
|
| 85 |
+
14157,
|
| 86 |
+
14635,
|
| 87 |
+
15265,
|
| 88 |
+
15618,
|
| 89 |
+
16553,
|
| 90 |
+
16604,
|
| 91 |
+
18362,
|
| 92 |
+
18956,
|
| 93 |
+
20075,
|
| 94 |
+
21675,
|
| 95 |
+
22520,
|
| 96 |
+
26130,
|
| 97 |
+
26161,
|
| 98 |
+
26435,
|
| 99 |
+
28279,
|
| 100 |
+
29464,
|
| 101 |
+
31650,
|
| 102 |
+
32302,
|
| 103 |
+
32470,
|
| 104 |
+
36865,
|
| 105 |
+
42863,
|
| 106 |
+
47425,
|
| 107 |
+
49870,
|
| 108 |
+
50254,
|
| 109 |
+
50258,
|
| 110 |
+
50358,
|
| 111 |
+
50359,
|
| 112 |
+
50360,
|
| 113 |
+
50361,
|
| 114 |
+
50362
|
| 115 |
+
],
|
| 116 |
+
"transformers_version": "4.27.4"
|
| 117 |
+
}
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"chunk_length": 30,
|
| 3 |
+
"feature_extractor_type": "WhisperFeatureExtractor",
|
| 4 |
+
"feature_size": 80,
|
| 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 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e0e980c39adb29670eda5b23206bc2eed3750c36ea59157b4ac6dfc53ecc9e4a
|
| 3 |
+
size 1656704956
|
runs/May12_11-49-28_galdor3.metacentrum.cz/1683884974.661549/events.out.tfevents.1683884974.galdor3.metacentrum.cz.887203.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:80c9ddc97150d2d7e9d88cc1e6645bc5fb7cc920a0cbdedab05d648381ed88c0
|
| 3 |
+
size 6144
|
runs/May12_11-49-28_galdor3.metacentrum.cz/events.out.tfevents.1683884974.galdor3.metacentrum.cz.887203.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3132b75abc30395174c01d92b97f00844dad294983e5d9733cc9684bcbfa7ddf
|
| 3 |
+
size 5097
|
runs/May12_11-51-14_galdor3.metacentrum.cz/1683885078.3930595/events.out.tfevents.1683885078.galdor3.metacentrum.cz.888975.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0746d2d50b062c0957cfb3073016b47de6a994aca51297ddba847e6eb2059460
|
| 3 |
+
size 6144
|
runs/May12_11-51-14_galdor3.metacentrum.cz/events.out.tfevents.1683885078.galdor3.metacentrum.cz.888975.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:158d30a52b1d62369acb9b4136d5cf222f1da832408616f9daca22147bad7b76
|
| 3 |
+
size 5097
|
runs/May12_11-52-47_galdor3.metacentrum.cz/1683885171.1735933/events.out.tfevents.1683885171.galdor3.metacentrum.cz.891624.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:afdafe7be977dfc2c3489fb20dc80abd187231e50845f1dbfa4edc62f9d38ace
|
| 3 |
+
size 6144
|
runs/May12_11-52-47_galdor3.metacentrum.cz/events.out.tfevents.1683885171.galdor3.metacentrum.cz.891624.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8a78ef30f4c3c17312b23c7bfa13e4667ac4ad98c063737fe3dd2d7ca1948682
|
| 3 |
+
size 14919
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5df841b1d0dafdf6d35d242344aa15438b154a92211b33e42b49992420c2a9f6
|
| 3 |
+
size 3835
|