Hugging Face's logo

jlvdoorn
/
whisper-large-v3-atco2-asr

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
whisper
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
jlvdoorn commited on
Commit
4c996fd
•
1 Parent(s): 7dba511

Training in progress, step 1000

Browse files
Files changed (7) hide show
  1. config.json +51 -0
  2. model.safetensors +3 -0
  3. preprocessor_config.json +14 -0
  4. runs/Nov10_05-43-09_gpu007/events.out.tfevents.1699591595.gpu007 +3 -0
  5. runs/Nov10_09-43-40_gpu009/events.out.tfevents.1699605839.gpu009 +3 -0
  6. runs/Nov10_10-21-56_gpu001/events.out.tfevents.1699608133.gpu001 +3 -0
  7. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "openai/whisper-large-v3",
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
+ 50256
13
+ ],
14
+ "bos_token_id": 50256,
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": 50257,
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": 50256,
28
+ "forced_decoder_ids": null,
29
+ "init_std": 0.02,
30
+ "is_encoder_decoder": true,
31
+ "mask_feature_length": 10,
32
+ "mask_feature_min_masks": 0,
33
+ "mask_feature_prob": 0.0,
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": 50256,
44
+ "scale_embedding": false,
45
+ "suppress_tokens": [],
46
+ "torch_dtype": "float16",
47
+ "transformers_version": "4.35.0",
48
+ "use_cache": true,
49
+ "use_weighted_layer_sum": false,
50
+ "vocab_size": 51866
51
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc8f08e37ffb1b37efba8f59ef7c21c0e0d151b209f1e45c7e62cb76d342a796
3
+ size 3219908024
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/Nov10_05-43-09_gpu007/events.out.tfevents.1699591595.gpu007 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ef9f1a223445f801f94ff1dfe696ab5f4edf15f701602b6fb091e1e3abb5cf3
3
+ size 12556
runs/Nov10_09-43-40_gpu009/events.out.tfevents.1699605839.gpu009 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e7ca816b72ca45a4f4090b1510ca4a621a644d13a695eaa913c641ac37c9e35
3
+ size 6103
runs/Nov10_10-21-56_gpu001/events.out.tfevents.1699608133.gpu001 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3686bff4581f8cd89006ce0f60b8abea2ed2c2f67811412e41d7cb2040f49778
3
+ size 12556
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d28980f4b0c36b1e1a4a773d1cfa259642b6852604621d47dfab63bf4f12e5e
3
+ size 5883