Model save

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+lm.arpa filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,9 +1,5 @@
 ---
-license: apache-2.0
-base_model: bofenghuang/asr-wav2vec2-ctc-french
 tags:
-- automatic-speech-recognition
-- mattlc/medical_internal_eval_22_mar_2024_noise_rir_2x
 - generated_from_trainer
 metrics:
 - wer
@@ -17,10 +13,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # wav2vec2-medical-internal-noise-v0
 
-This model is a fine-tuned version of [bofenghuang/asr-wav2vec2-ctc-french](https://huggingface.co/bofenghuang/asr-wav2vec2-ctc-french) on the MATTLC/MEDICAL_INTERNAL_EVAL_22_MAR_2024_NOISE_RIR_2X - NA dataset.
+This model was trained from scratch on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.5827
-- Wer: 0.3319
+- Loss: 0.6016
+- Wer: 0.3413
 
 ## Model description
 

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "bofenghuang/asr-wav2vec2-ctc-french",
+  "_name_or_path": "/home/tranceformer/whisper-text-domain-enhance/models/wav2vec2-medical-internal-noise-v0",
   "activation_dropout": 0.0,
   "adapter_attn_dim": null,
   "adapter_kernel_size": 3,

lm.arpa

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:162d92a03b3a8084a385ca8c321e095f93ff9528372d1d26aa9bb12950e71494
+size 479608759

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb4db5f36c4ffb262b701214d847768c74f073d576be8f9447a755f04521ff6e
+oid sha256:80c3c975ba443a304094adc8ab387fa7c8c9091ba01bd4d87d6b793d57f6ec45
 size 1262012432

runs/Apr17_14-41-03_tranceformer/events.out.tfevents.1713364982.tranceformer.212254.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b5aaf7af7ee32d367a027b3434af2c71d153685e3212479ee9b42c21edd477e
+size 7317

special_tokens_map.json

@@ -1,21 +1,15 @@
 {
   "additional_special_tokens": [
-    {
-      "content": "<s>",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false
-    },
-    {
-      "content": "</s>",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false
-    }
+    "<s>",
+    "</s>"
   ],
-  "bos_token": "<s>",
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
   "eos_token": {
     "content": "<s>",
     "lstrip": false,
@@ -23,6 +17,18 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "[PAD]",
-  "unk_token": "[UNK]"
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": true,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": true,
+    "single_word": false
+  }
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:841d119f6d8b494c9270d5e27fed2f43a442017dbbf37b1fe5d2171b3068b3d1
+oid sha256:6ab7c93030ee0675f7cb62ef84fae937633275f393809179d1c97eb8efc9f8a9
 size 4603