Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
Russian
wav2vec2
Generated from Trainer
hf-asr-leaderboard
robust-speech-event
Eval Results (legacy)
Instructions to use emre/wav2vec2-xls-r-300m-Russian-small with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use emre/wav2vec2-xls-r-300m-Russian-small with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="emre/wav2vec2-xls-r-300m-Russian-small")# Load model directly from transformers import AutoProcessor, AutoModelForCTC processor = AutoProcessor.from_pretrained("emre/wav2vec2-xls-r-300m-Russian-small") model = AutoModelForCTC.from_pretrained("emre/wav2vec2-xls-r-300m-Russian-small", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Training in progress, step 400
Browse files- .gitignore +1 -0
- config.json +79 -0
- preprocessor_config.json +9 -0
- pytorch_model.bin +3 -0
- runs/Jan26_12-29-31_3d71c44f1634/1643200416.5478368/events.out.tfevents.1643200416.3d71c44f1634.84.1 +3 -0
- runs/Jan26_12-29-31_3d71c44f1634/events.out.tfevents.1643200416.3d71c44f1634.84.0 +3 -0
- runs/Jan26_12-35-16_3d71c44f1634/1643200750.353069/events.out.tfevents.1643200750.3d71c44f1634.84.3 +3 -0
- runs/Jan26_12-35-16_3d71c44f1634/events.out.tfevents.1643200750.3d71c44f1634.84.2 +3 -0
- training_args.bin +3 -0
.gitignore
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
checkpoint-*/
|
config.json
ADDED
|
@@ -0,0 +1,79 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "facebook/wav2vec2-xls-r-300m",
|
| 3 |
+
"activation_dropout": 0.0,
|
| 4 |
+
"apply_spec_augment": true,
|
| 5 |
+
"architectures": [
|
| 6 |
+
"Wav2Vec2ForCTC"
|
| 7 |
+
],
|
| 8 |
+
"attention_dropout": 0.1,
|
| 9 |
+
"bos_token_id": 1,
|
| 10 |
+
"classifier_proj_size": 256,
|
| 11 |
+
"codevector_dim": 768,
|
| 12 |
+
"contrastive_logits_temperature": 0.1,
|
| 13 |
+
"conv_bias": true,
|
| 14 |
+
"conv_dim": [
|
| 15 |
+
512,
|
| 16 |
+
512,
|
| 17 |
+
512,
|
| 18 |
+
512,
|
| 19 |
+
512,
|
| 20 |
+
512,
|
| 21 |
+
512
|
| 22 |
+
],
|
| 23 |
+
"conv_kernel": [
|
| 24 |
+
10,
|
| 25 |
+
3,
|
| 26 |
+
3,
|
| 27 |
+
3,
|
| 28 |
+
3,
|
| 29 |
+
2,
|
| 30 |
+
2
|
| 31 |
+
],
|
| 32 |
+
"conv_stride": [
|
| 33 |
+
5,
|
| 34 |
+
2,
|
| 35 |
+
2,
|
| 36 |
+
2,
|
| 37 |
+
2,
|
| 38 |
+
2,
|
| 39 |
+
2
|
| 40 |
+
],
|
| 41 |
+
"ctc_loss_reduction": "mean",
|
| 42 |
+
"ctc_zero_infinity": false,
|
| 43 |
+
"diversity_loss_weight": 0.1,
|
| 44 |
+
"do_stable_layer_norm": true,
|
| 45 |
+
"eos_token_id": 2,
|
| 46 |
+
"feat_extract_activation": "gelu",
|
| 47 |
+
"feat_extract_dropout": 0.0,
|
| 48 |
+
"feat_extract_norm": "layer",
|
| 49 |
+
"feat_proj_dropout": 0.0,
|
| 50 |
+
"feat_quantizer_dropout": 0.0,
|
| 51 |
+
"final_dropout": 0.0,
|
| 52 |
+
"gradient_checkpointing": false,
|
| 53 |
+
"hidden_act": "gelu",
|
| 54 |
+
"hidden_dropout": 0.1,
|
| 55 |
+
"hidden_size": 1024,
|
| 56 |
+
"initializer_range": 0.02,
|
| 57 |
+
"intermediate_size": 4096,
|
| 58 |
+
"layer_norm_eps": 1e-05,
|
| 59 |
+
"layerdrop": 0.1,
|
| 60 |
+
"mask_feature_length": 10,
|
| 61 |
+
"mask_feature_prob": 0.0,
|
| 62 |
+
"mask_time_length": 10,
|
| 63 |
+
"mask_time_prob": 0.05,
|
| 64 |
+
"model_type": "wav2vec2",
|
| 65 |
+
"num_attention_heads": 16,
|
| 66 |
+
"num_codevector_groups": 2,
|
| 67 |
+
"num_codevectors_per_group": 320,
|
| 68 |
+
"num_conv_pos_embedding_groups": 16,
|
| 69 |
+
"num_conv_pos_embeddings": 128,
|
| 70 |
+
"num_feat_extract_layers": 7,
|
| 71 |
+
"num_hidden_layers": 24,
|
| 72 |
+
"num_negatives": 100,
|
| 73 |
+
"pad_token_id": 64,
|
| 74 |
+
"proj_codevector_dim": 768,
|
| 75 |
+
"torch_dtype": "float32",
|
| 76 |
+
"transformers_version": "4.11.3",
|
| 77 |
+
"use_weighted_layer_sum": false,
|
| 78 |
+
"vocab_size": 67
|
| 79 |
+
}
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_normalize": true,
|
| 3 |
+
"feature_extractor_type": "Wav2Vec2FeatureExtractor",
|
| 4 |
+
"feature_size": 1,
|
| 5 |
+
"padding_side": "right",
|
| 6 |
+
"padding_value": 0,
|
| 7 |
+
"return_attention_mask": true,
|
| 8 |
+
"sampling_rate": 16000
|
| 9 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d240a7d23ff14db8c4b64607010e58ce956d291b715963881371584454fe311d
|
| 3 |
+
size 1262198385
|
runs/Jan26_12-29-31_3d71c44f1634/1643200416.5478368/events.out.tfevents.1643200416.3d71c44f1634.84.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7233706df27f0a89fe7a72437fb5c19b48f0d7dcd362c113c7de6b3e100e456a
|
| 3 |
+
size 4564
|
runs/Jan26_12-29-31_3d71c44f1634/events.out.tfevents.1643200416.3d71c44f1634.84.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:340634bcf20e17cb4738bcd258d9000394d7556132eb2c89f6046de4831f798b
|
| 3 |
+
size 4219
|
runs/Jan26_12-35-16_3d71c44f1634/1643200750.353069/events.out.tfevents.1643200750.3d71c44f1634.84.3
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:95c5f0122c7f8c402bcf4b3932a1ae5e151368750c18c90cdb37cea5d10ea12f
|
| 3 |
+
size 4564
|
runs/Jan26_12-35-16_3d71c44f1634/events.out.tfevents.1643200750.3d71c44f1634.84.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:281215339ba7b85b2587e4e0247a18658e1d519b033085d6f7480494a57902c0
|
| 3 |
+
size 4694
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d6e0a661e51cffe58ae0567fca426287df943005d28dec8c2b566c28fef60339
|
| 3 |
+
size 2863
|