Instructions to use ghost613/VC-yu7361-BLSTM-cleaner-ctc with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ghost613/VC-yu7361-BLSTM-cleaner-ctc with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("ghost613/VC-yu7361-BLSTM-cleaner-ctc", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Training in progress, epoch 3
Browse files
config.json
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"WhisperPhonemePredictionModel"
|
| 4 |
+
],
|
| 5 |
+
"blank": 0,
|
| 6 |
+
"decoder": "BLSTM",
|
| 7 |
+
"dropout_rate": 0.1,
|
| 8 |
+
"dtype": "float32",
|
| 9 |
+
"freeze_encoder": true,
|
| 10 |
+
"hidden_dim": 512,
|
| 11 |
+
"id_2_phoneme": {
|
| 12 |
+
"0": "\u2205",
|
| 13 |
+
"1": "\u3131",
|
| 14 |
+
"2": "\u3132",
|
| 15 |
+
"3": "\u3134",
|
| 16 |
+
"4": "\u3137",
|
| 17 |
+
"5": "\u3138",
|
| 18 |
+
"6": "\u3139",
|
| 19 |
+
"7": "\u3141",
|
| 20 |
+
"8": "\u3142",
|
| 21 |
+
"9": "\u3143",
|
| 22 |
+
"10": "\u3145",
|
| 23 |
+
"11": "\u3146",
|
| 24 |
+
"12": "\u3147",
|
| 25 |
+
"13": "\u3148",
|
| 26 |
+
"14": "\u3149",
|
| 27 |
+
"15": "\u314a",
|
| 28 |
+
"16": "\u314b",
|
| 29 |
+
"17": "\u314c",
|
| 30 |
+
"18": "\u314d",
|
| 31 |
+
"19": "\u314e",
|
| 32 |
+
"20": "\u314f",
|
| 33 |
+
"21": "\u3150",
|
| 34 |
+
"22": "\u3151",
|
| 35 |
+
"23": "\u3152",
|
| 36 |
+
"24": "\u3153",
|
| 37 |
+
"25": "\u3154",
|
| 38 |
+
"26": "\u3155",
|
| 39 |
+
"27": "\u3156",
|
| 40 |
+
"28": "\u3157",
|
| 41 |
+
"29": "\u3158",
|
| 42 |
+
"30": "\u3159",
|
| 43 |
+
"31": "\u315a",
|
| 44 |
+
"32": "\u315b",
|
| 45 |
+
"33": "\u315c",
|
| 46 |
+
"34": "\u315d",
|
| 47 |
+
"35": "\u315e",
|
| 48 |
+
"36": "\u315f",
|
| 49 |
+
"37": "\u3160",
|
| 50 |
+
"38": "\u3161",
|
| 51 |
+
"39": "\u3162",
|
| 52 |
+
"40": "\u3163"
|
| 53 |
+
},
|
| 54 |
+
"model_name": "openai/whisper-large-v3-turbo",
|
| 55 |
+
"model_type": "whisper_phoneme",
|
| 56 |
+
"phoneme_vocab_size": 41,
|
| 57 |
+
"transformers_version": "4.57.0"
|
| 58 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7552f451431c88b4822229e7a78e62d2ea7bf70d0b0d7677055c8b6494d05826
|
| 3 |
+
size 2631912028
|
runs/Oct14_20-05-59_ali02/events.out.tfevents.1760439970.ali02.480901.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aba9de4d148d202f1ed1822f664e3fe5fec25d82d3e6ebf6f5813500cd1ffe45
|
| 3 |
+
size 6916
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:238e39c7ed049db13349dea7c398fa5d4ef0ac6f5b833861582aa29ec646eeaf
|
| 3 |
+
size 5560
|