lighteternal
commited on
Commit
•
e5de2d3
1
Parent(s):
2c4a267
Added new model trained on 60 epochs
Browse files- README.md +9 -6
- wav2vec2-large-xlsr-greek/checkpoint-18400/config.json → config.json +0 -0
- wav2vec2-large-xlsr-greek/checkpoint-18400/preprocessor_config.json → preprocessor_config.json +0 -0
- wav2vec2-large-xlsr-greek/checkpoint-18400/pytorch_model.bin → pytorch_model.bin +0 -0
- wav2vec2-large-xlsr-greek/special_tokens_map.json → special_tokens_map.json +0 -0
- wav2vec2-large-xlsr-greek/tokenizer_config.json → tokenizer_config.json +0 -0
- wav2vec2-large-xlsr-greek/checkpoint-18400/trainer_state.json → trainer_state.json +0 -0
- wav2vec2-large-xlsr-greek/checkpoint-18400/training_args.bin → training_args.bin +0 -0
- vocab.json +1 -1
- wav2vec2-large-xlsr-greek/checkpoint-18400/optimizer.pt +0 -3
- wav2vec2-large-xlsr-greek/checkpoint-18400/scheduler.pt +0 -3
- wav2vec2-large-xlsr-greek/preprocessor_config.json +0 -8
- wav2vec2-large-xlsr-greek/vocab.json +0 -1
README.md
CHANGED
@@ -1,12 +1,13 @@
|
|
1 |
|
2 |
---
|
3 |
-
language:
|
4 |
-
|
|
|
5 |
tags:
|
6 |
-
-
|
7 |
-
-
|
8 |
-
|
9 |
-
|
10 |
---
|
11 |
|
12 |
# Greek (el) version of the XLSR-Wav2Vec2 automatic speech recognition (ASR) model
|
@@ -28,6 +29,8 @@ This model was trained on Greek CommonVoice speech data (364MB) for 30 epochs on
|
|
28 |
|
29 |
### How to use for inference:
|
30 |
|
|
|
|
|
31 |
Instructions to test on CommonVoice extracts are provided in the ASR_Inference.ipynb. Snippet also available below:
|
32 |
|
33 |
```
|
|
|
1 |
|
2 |
---
|
3 |
+
language: el
|
4 |
+
datasets:
|
5 |
+
- common_voice
|
6 |
tags:
|
7 |
+
- speech
|
8 |
+
- audio
|
9 |
+
- automatic-speech-recognition
|
10 |
+
license: apache-2.0
|
11 |
---
|
12 |
|
13 |
# Greek (el) version of the XLSR-Wav2Vec2 automatic speech recognition (ASR) model
|
|
|
29 |
|
30 |
### How to use for inference:
|
31 |
|
32 |
+
For live demo, make sure that speech files are sampled at 16kHz.
|
33 |
+
|
34 |
Instructions to test on CommonVoice extracts are provided in the ASR_Inference.ipynb. Snippet also available below:
|
35 |
|
36 |
```
|
wav2vec2-large-xlsr-greek/checkpoint-18400/config.json → config.json
RENAMED
File without changes
|
wav2vec2-large-xlsr-greek/checkpoint-18400/preprocessor_config.json → preprocessor_config.json
RENAMED
File without changes
|
wav2vec2-large-xlsr-greek/checkpoint-18400/pytorch_model.bin → pytorch_model.bin
RENAMED
File without changes
|
wav2vec2-large-xlsr-greek/special_tokens_map.json → special_tokens_map.json
RENAMED
File without changes
|
wav2vec2-large-xlsr-greek/tokenizer_config.json → tokenizer_config.json
RENAMED
File without changes
|
wav2vec2-large-xlsr-greek/checkpoint-18400/trainer_state.json → trainer_state.json
RENAMED
File without changes
|
wav2vec2-large-xlsr-greek/checkpoint-18400/training_args.bin → training_args.bin
RENAMED
File without changes
|
vocab.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"
|
|
|
1 |
+
{"ώ": 0, "γ": 1, "n": 2, "ϋ": 3, "κ": 4, "e": 5, "ξ": 6, "'": 7, "θ": 8, "’": 9, "σ": 10, "η": 11, "ι": 12, "α": 13, "ε": 14, "υ": 15, "v": 16, "μ": 17, "ο": 18, "«": 19, "»": 20, "έ": 21, "ν": 22, "ά": 24, "o": 25, "ζ": 26, "β": 27, "τ": 28, "π": 29, "ή": 30, "ψ": 31, "ΐ": 32, "ό": 33, "h": 34, "ύ": 35, "ω": 36, "´": 37, "χ": 38, "ϊ": 39, "ρ": 40, "a": 41, "ς": 42, "r": 43, "g": 44, "m": 45, "λ": 46, "́": 47, "ί": 48, "φ": 49, "δ": 50, "|": 23, "[UNK]": 51, "[PAD]": 52}
|
wav2vec2-large-xlsr-greek/checkpoint-18400/optimizer.pt
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:272a2cd55e47d89c16aadfc21a5186b3c1ee4f0dd61f67d1dfbe6e325392f208
|
3 |
-
size 2490511751
|
|
|
|
|
|
|
|
wav2vec2-large-xlsr-greek/checkpoint-18400/scheduler.pt
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:191d69c70a4b492d24ee1d59dad04edf9839c09a08b9cc6bd41530cfdaa0092c
|
3 |
-
size 623
|
|
|
|
|
|
|
|
wav2vec2-large-xlsr-greek/preprocessor_config.json
DELETED
@@ -1,8 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"do_normalize": true,
|
3 |
-
"feature_size": 1,
|
4 |
-
"padding_side": "right",
|
5 |
-
"padding_value": 0.0,
|
6 |
-
"return_attention_mask": true,
|
7 |
-
"sampling_rate": 16000
|
8 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
wav2vec2-large-xlsr-greek/vocab.json
DELETED
@@ -1 +0,0 @@
|
|
1 |
-
{"ώ": 0, "γ": 1, "n": 2, "ϋ": 3, "κ": 4, "e": 5, "ξ": 6, "'": 7, "θ": 8, "’": 9, "σ": 10, "η": 11, "ι": 12, "α": 13, "ε": 14, "υ": 15, "v": 16, "μ": 17, "ο": 18, "«": 19, "»": 20, "έ": 21, "ν": 22, "ά": 24, "o": 25, "ζ": 26, "β": 27, "τ": 28, "π": 29, "ή": 30, "ψ": 31, "ΐ": 32, "ό": 33, "h": 34, "ύ": 35, "ω": 36, "´": 37, "χ": 38, "ϊ": 39, "ρ": 40, "a": 41, "ς": 42, "r": 43, "g": 44, "m": 45, "λ": 46, "́": 47, "ί": 48, "φ": 49, "δ": 50, "|": 23, "[UNK]": 51, "[PAD]": 52}
|
|
|
|