Training in progress, step 1000
Browse files
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "openai/whisper-large-v3",
|
3 |
"activation_dropout": 0.0,
|
4 |
"activation_function": "gelu",
|
5 |
"apply_spec_augment": false,
|
@@ -9,7 +9,7 @@
|
|
9 |
"attention_dropout": 0.0,
|
10 |
"begin_suppress_tokens": [
|
11 |
220,
|
12 |
-
|
13 |
],
|
14 |
"bos_token_id": 50257,
|
15 |
"classifier_proj_size": 256,
|
@@ -17,7 +17,7 @@
|
|
17 |
"decoder_attention_heads": 20,
|
18 |
"decoder_ffn_dim": 5120,
|
19 |
"decoder_layerdrop": 0.0,
|
20 |
-
"decoder_layers":
|
21 |
"decoder_start_token_id": 50258,
|
22 |
"dropout": 0.0,
|
23 |
"encoder_attention_heads": 20,
|
@@ -34,18 +34,16 @@
|
|
34 |
"mask_time_length": 10,
|
35 |
"mask_time_min_masks": 2,
|
36 |
"mask_time_prob": 0.05,
|
37 |
-
"max_length": 448,
|
38 |
"max_source_positions": 1500,
|
39 |
"max_target_positions": 448,
|
40 |
"median_filter_width": 7,
|
41 |
"model_type": "whisper",
|
42 |
"num_hidden_layers": 32,
|
43 |
"num_mel_bins": 128,
|
44 |
-
"pad_token_id":
|
45 |
"scale_embedding": false,
|
46 |
-
"suppress_tokens": [],
|
47 |
"torch_dtype": "float32",
|
48 |
-
"transformers_version": "4.
|
49 |
"use_cache": true,
|
50 |
"use_weighted_layer_sum": false,
|
51 |
"vocab_size": 51866
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "openai/whisper-large-v3-turbo",
|
3 |
"activation_dropout": 0.0,
|
4 |
"activation_function": "gelu",
|
5 |
"apply_spec_augment": false,
|
|
|
9 |
"attention_dropout": 0.0,
|
10 |
"begin_suppress_tokens": [
|
11 |
220,
|
12 |
+
50256
|
13 |
],
|
14 |
"bos_token_id": 50257,
|
15 |
"classifier_proj_size": 256,
|
|
|
17 |
"decoder_attention_heads": 20,
|
18 |
"decoder_ffn_dim": 5120,
|
19 |
"decoder_layerdrop": 0.0,
|
20 |
+
"decoder_layers": 4,
|
21 |
"decoder_start_token_id": 50258,
|
22 |
"dropout": 0.0,
|
23 |
"encoder_attention_heads": 20,
|
|
|
34 |
"mask_time_length": 10,
|
35 |
"mask_time_min_masks": 2,
|
36 |
"mask_time_prob": 0.05,
|
|
|
37 |
"max_source_positions": 1500,
|
38 |
"max_target_positions": 448,
|
39 |
"median_filter_width": 7,
|
40 |
"model_type": "whisper",
|
41 |
"num_hidden_layers": 32,
|
42 |
"num_mel_bins": 128,
|
43 |
+
"pad_token_id": 50257,
|
44 |
"scale_embedding": false,
|
|
|
45 |
"torch_dtype": "float32",
|
46 |
+
"transformers_version": "4.47.0.dev0",
|
47 |
"use_cache": true,
|
48 |
"use_weighted_layer_sum": false,
|
49 |
"vocab_size": 51866
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2985f36c45745745c7f7c7d5079ae773b534671755a0697ff212fcf45610f3eb
|
3 |
+
size 3235581408
|
runs/Dec05_14-17-07_a35b2528692b/events.out.tfevents.1733408247.a35b2528692b.486.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cc857b2c53d8a415314cc3465e217cebcc386e3849941d64082a0a93e4f4b99f
|
3 |
+
size 14627
|
tokenizer_config.json
CHANGED
@@ -12987,6 +12987,7 @@
|
|
12987 |
"clean_up_tokenization_spaces": true,
|
12988 |
"eos_token": "<|endoftext|>",
|
12989 |
"errors": "replace",
|
|
|
12990 |
"model_max_length": 1000000000000000019884624838656,
|
12991 |
"pad_token": "<|endoftext|>",
|
12992 |
"processor_class": "WhisperProcessor",
|
|
|
12987 |
"clean_up_tokenization_spaces": true,
|
12988 |
"eos_token": "<|endoftext|>",
|
12989 |
"errors": "replace",
|
12990 |
+
"extra_special_tokens": {},
|
12991 |
"model_max_length": 1000000000000000019884624838656,
|
12992 |
"pad_token": "<|endoftext|>",
|
12993 |
"processor_class": "WhisperProcessor",
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:01e26c2f51a6e826cb4ad97120ecc89360ba3e22e0b7cfde7899f17621125662
|
3 |
+
size 5496
|