Upload Speech2TextEncoderForCTC
Browse files- config.json +43 -0
- model.safetensors +3 -0
config.json
ADDED
|
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation_dropout": 0.0,
|
| 3 |
+
"activation_function": "relu",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"Speech2TextEncoderForCTC"
|
| 6 |
+
],
|
| 7 |
+
"attention_dropout": 0.0,
|
| 8 |
+
"bos_token_id": 0,
|
| 9 |
+
"conv_channels": 1024,
|
| 10 |
+
"conv_kernel_sizes": [
|
| 11 |
+
5,
|
| 12 |
+
5
|
| 13 |
+
],
|
| 14 |
+
"ctc_vocab_size": 32,
|
| 15 |
+
"ctc_zero_infinity": false,
|
| 16 |
+
"d_model": 256,
|
| 17 |
+
"decoder_attention_heads": 4,
|
| 18 |
+
"decoder_ffn_dim": 2048,
|
| 19 |
+
"decoder_layerdrop": 0.0,
|
| 20 |
+
"decoder_layers": 6,
|
| 21 |
+
"decoder_start_token_id": 2,
|
| 22 |
+
"dropout": 0.1,
|
| 23 |
+
"encoder_attention_heads": 4,
|
| 24 |
+
"encoder_ffn_dim": 2048,
|
| 25 |
+
"encoder_layerdrop": 0.0,
|
| 26 |
+
"encoder_layers": 12,
|
| 27 |
+
"eos_token_id": 2,
|
| 28 |
+
"init_std": 0.02,
|
| 29 |
+
"input_channels": 1,
|
| 30 |
+
"input_feat_per_channel": 80,
|
| 31 |
+
"is_encoder_decoder": true,
|
| 32 |
+
"max_source_positions": 6000,
|
| 33 |
+
"max_target_positions": 1024,
|
| 34 |
+
"model_type": "s2t-ctc-encoder",
|
| 35 |
+
"num_conv_layers": 2,
|
| 36 |
+
"num_hidden_layers": 12,
|
| 37 |
+
"pad_token_id": 1,
|
| 38 |
+
"scale_embedding": true,
|
| 39 |
+
"torch_dtype": "float32",
|
| 40 |
+
"transformers_version": "4.36.2",
|
| 41 |
+
"use_cache": true,
|
| 42 |
+
"vocab_size": 8000
|
| 43 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1bff7ec293f1ab4e713c0b3f717035292ad185b0f48edf357da6dec4fd02aba6
|
| 3 |
+
size 84404288
|