Upload folder using huggingface_hub
Browse files- config.json +48 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- preprocessor_config.json +15 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +0 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation_dropout": 0.0,
|
| 3 |
+
"activation_function": "gelu",
|
| 4 |
+
"apply_spec_augment": false,
|
| 5 |
+
"architectures": [
|
| 6 |
+
"WhisperForAudioClassification"
|
| 7 |
+
],
|
| 8 |
+
"attention_dropout": 0.0,
|
| 9 |
+
"begin_suppress_tokens": [
|
| 10 |
+
220,
|
| 11 |
+
50256
|
| 12 |
+
],
|
| 13 |
+
"bos_token_id": 50257,
|
| 14 |
+
"classifier_proj_size": 256,
|
| 15 |
+
"d_model": 1280,
|
| 16 |
+
"decoder_attention_heads": 20,
|
| 17 |
+
"decoder_ffn_dim": 5120,
|
| 18 |
+
"decoder_layerdrop": 0.0,
|
| 19 |
+
"decoder_layers": 4,
|
| 20 |
+
"decoder_start_token_id": 50258,
|
| 21 |
+
"dropout": 0.0,
|
| 22 |
+
"dtype": "float32",
|
| 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 |
+
"init_std": 0.02,
|
| 29 |
+
"is_encoder_decoder": true,
|
| 30 |
+
"mask_feature_length": 10,
|
| 31 |
+
"mask_feature_min_masks": 0,
|
| 32 |
+
"mask_feature_prob": 0.0,
|
| 33 |
+
"mask_time_length": 10,
|
| 34 |
+
"mask_time_min_masks": 2,
|
| 35 |
+
"mask_time_prob": 0.05,
|
| 36 |
+
"max_source_positions": 50,
|
| 37 |
+
"max_target_positions": 448,
|
| 38 |
+
"median_filter_width": 7,
|
| 39 |
+
"model_type": "whisper",
|
| 40 |
+
"num_hidden_layers": 32,
|
| 41 |
+
"num_mel_bins": 128,
|
| 42 |
+
"pad_token_id": 50257,
|
| 43 |
+
"scale_embedding": false,
|
| 44 |
+
"transformers_version": "4.57.3",
|
| 45 |
+
"use_cache": true,
|
| 46 |
+
"use_weighted_layer_sum": false,
|
| 47 |
+
"vocab_size": 51866
|
| 48 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6415c3233f87f6a55497463250fafcc55afa81df0bcaeae9971a34d2cd771e52
|
| 3 |
+
size 2541820056
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:36e090dee3c9a878e5fb12024bb4e3250034ca4d4d21603e2227f4bd483322c7
|
| 3 |
+
size 5083449089
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"chunk_length": 30,
|
| 3 |
+
"dither": 0.0,
|
| 4 |
+
"feature_extractor_type": "WhisperFeatureExtractor",
|
| 5 |
+
"feature_size": 128,
|
| 6 |
+
"hop_length": 160,
|
| 7 |
+
"n_fft": 400,
|
| 8 |
+
"n_samples": 480000,
|
| 9 |
+
"nb_max_frames": 3000,
|
| 10 |
+
"padding_side": "right",
|
| 11 |
+
"padding_value": 0.0,
|
| 12 |
+
"processor_class": "WhisperProcessor",
|
| 13 |
+
"return_attention_mask": false,
|
| 14 |
+
"sampling_rate": 16000
|
| 15 |
+
}
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e89f0a0ec0edd9bd3779125895c2472940f773e3450c40cc62b74aa510cafe19
|
| 3 |
+
size 14645
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d365950bc9de69c0a55de0223cf089e11e5b7b11d477a1c340e3418bfaede98b
|
| 3 |
+
size 1465
|
trainer_state.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:af22b4baf384ceadd1a5a974c034a455077a83d643efef6f2c060f4a89a3d8c5
|
| 3 |
+
size 5841
|