Enpas commited on
Commit
895c18c
·
verified ·
1 Parent(s): 15ef137

Training in progress, step 1000

Browse files
config.json ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_dropout": 0.0,
3
+ "activation_function": "gelu",
4
+ "apply_spec_augment": false,
5
+ "architectures": [
6
+ "WhisperForConditionalGeneration"
7
+ ],
8
+ "attention_dropout": 0.0,
9
+ "begin_suppress_tokens": null,
10
+ "bos_token_id": 0,
11
+ "classifier_proj_size": 256,
12
+ "d_model": 512,
13
+ "decoder_attention_heads": 8,
14
+ "decoder_ffn_dim": 2048,
15
+ "decoder_layerdrop": 0.0,
16
+ "decoder_layers": 6,
17
+ "decoder_start_token_id": 0,
18
+ "dropout": 0.0,
19
+ "encoder_attention_heads": 8,
20
+ "encoder_ffn_dim": 2048,
21
+ "encoder_layerdrop": 0.0,
22
+ "encoder_layers": 6,
23
+ "eos_token_id": 1,
24
+ "forced_decoder_ids": null,
25
+ "init_std": 0.02,
26
+ "is_encoder_decoder": true,
27
+ "language": "amharic",
28
+ "mask_feature_length": 10,
29
+ "mask_feature_min_masks": 0,
30
+ "mask_feature_prob": 0.0,
31
+ "mask_time_length": 10,
32
+ "mask_time_min_masks": 2,
33
+ "mask_time_prob": 0.05,
34
+ "max_length": null,
35
+ "max_source_positions": 1500,
36
+ "max_target_positions": 448,
37
+ "median_filter_width": 7,
38
+ "model_type": "whisper",
39
+ "num_hidden_layers": 6,
40
+ "num_mel_bins": 80,
41
+ "pad_token_id": 3,
42
+ "scale_embedding": false,
43
+ "task": "transcribe",
44
+ "torch_dtype": "float32",
45
+ "transformers_version": "4.51.3",
46
+ "use_cache": false,
47
+ "use_weighted_layer_sum": false,
48
+ "vocab_size": 8000
49
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f382ec72e8fba9b3a08bd7802fbd16e8a1337bb731d99b3b37d2f61deb4f739
3
+ size 200568176
preprocessor_config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "chunk_length": 30,
3
+ "dither": 0.0,
4
+ "do_normalize": true,
5
+ "feature_extractor_type": "WhisperFeatureExtractor",
6
+ "feature_size": 80,
7
+ "hop_length": 160,
8
+ "n_fft": 400,
9
+ "n_samples": 480000,
10
+ "nb_max_frames": 3000,
11
+ "padding_side": "right",
12
+ "padding_value": 0.0,
13
+ "processor_class": "WhisperProcessor",
14
+ "return_attention_mask": false,
15
+ "sampling_rate": 16000
16
+ }
runs/May11_17-58-21_bba71e0e77f6/events.out.tfevents.1746986302.bba71e0e77f6.19.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fad67b11447cadd4d44438d3753e782b21ce5bd65416aadf073000abcd2bb6d4
3
+ size 8078
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|startoftranscript|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<pad>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff
 
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:abc320d1f03327e5227fac353628f457cfab90d453fabc71263f8cfb39bc6108
3
+ size 5432
vocab.json ADDED
The diff for this file is too large to render. See raw diff