Roberh18 commited on
Commit
ea40c2e
Β·
verified Β·
1 Parent(s): 898005c

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +50 -1
README.md CHANGED
@@ -1,3 +1,52 @@
1
  ---
2
- license: mit
 
 
 
 
 
 
 
 
 
 
 
 
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
+ license: other
3
+ language:
4
+ - en
5
+ tags:
6
+ - automatic-speech-recognition
7
+ - speech-recognition
8
+ - state-space-models
9
+ - mamba
10
+ - ctc
11
+ - librispeech
12
+ - pytorch
13
+ - masters-thesis
14
+ pretty_name: SSM-AST thesis checkpoints
15
  ---
16
+
17
+ # SSM-AST: State Space Models for Automatic Speech Transcription
18
+
19
+ This repository contains model artifacts for the master's thesis **β€œState Space Models for Automatic Speech Transcription.”** It provides the trained acoustic encoder checkpoints, language-model checkpoints, n-gram training text, and selected training logs used to support evaluation of a pure State Space Model (SSM) automatic speech transcription pipeline on LibriSpeech.
20
+
21
+ The code for training and evaluation is maintained separately. This Hugging Face repository is intended as a checkpoint and artifact archive so that the thesis evaluation pipeline can be run without retraining the full models from scratch.
22
+
23
+ ## Repository contents
24
+
25
+ ```text
26
+ SSM-AST/
27
+ β”œβ”€β”€ datasets/
28
+ β”‚ └── librispeecm_lm_dataset_pre-processed_char_level_text.txt
29
+ β”œβ”€β”€ encoder_checkpoints/
30
+ β”‚ β”œβ”€β”€ enc_mamba3_460h_checkpoint_best_epoch=49_val_wer=0.255.ckpt
31
+ β”‚ β”œβ”€β”€ enc_mamba3_960h_checkpoint_best_epoch=91_val_wer=0.186.ckpt
32
+ β”‚ β”œβ”€β”€ enc_mamba_460h_checkpoint_best_epoch=49_val_wer=0.227.ckpt
33
+ β”‚ β”œβ”€β”€ enc_mamba_960h_checkpoint_best_epoch=100_val_wer=0.155.ckpt
34
+ β”‚ β”œβ”€β”€ enc_ssssm_460h_checkpoint_best_epoch=49_val_wer=0.197.ckpt
35
+ β”‚ β”œβ”€β”€ enc_ssssm_960h_checkpoint_best_epoch=100_val_wer=0.111.ckpt
36
+ β”‚ └── enc_ssssm_960h_checkpoint_best_epoch=98_val_wer=0.111.ckpt
37
+ β”œβ”€β”€ lm_checkpoints/
38
+ β”‚ β”œβ”€β”€ lm_mamba3_checkpoint_MaxChars-1000000000_ds-64_d320_L18.pt
39
+ β”‚ β”œβ”€β”€ lm_mamba_checkpoint_MaxChars-1000000000_d320_L18.pt
40
+ β”‚ └── lm_ngram_checkpoint_char_10gram.pkl
41
+ β”œβ”€β”€ log files/
42
+ β”‚ β”œβ”€β”€ 0utput_exp-mamba-1_960h_W-320_D-48_S-16_B-128_E-100.txt
43
+ β”‚ β”œβ”€β”€ 0utput_exp-mamba3_460h_W-512_D-30_S-16_B-64_E-50.txt
44
+ β”‚ β”œβ”€β”€ 0utput_exp-mamba3_enc_960h_W-320_D-48_S-16_b-64_E-100.txt
45
+ β”‚ β”œβ”€β”€ 0utput_exp-mamba_dt_bias_hier_460h_W-512_D-30_S-16.txt
46
+ β”‚ β”œβ”€β”€ 0utput_exp-v75_460h_hier_gating_256_42.txt
47
+ β”‚ β”œβ”€β”€ 0utput_exp-v77_960h_hier_gating_320_48.txt
48
+ β”‚ β”œβ”€β”€ mamba3_elm_training.log
49
+ β”‚ └── mamba_elm_training.log
50
+ β”œβ”€β”€ .gitattributes
51
+ └── README.md
52
+ ```