Upload model

README.md

@@ -1,57 +1,9 @@
 ---
-license: cc-by-nc-4.0
-base_model: Umong/wav2vec2-large-mms-1b-bengali
-tags:
-- generated_from_trainer
-model-index:
-- name: Umong/wav2vec2-large-mms-1b-bengali
-  results: []
+library_name: peft
 ---
-
-<!-- This model card has been generated automatically according to the information the Trainer had access to. You
-should probably proofread and complete it, then remove this comment. -->
-
-# Umong/wav2vec2-large-mms-1b-bengali
-
-This model is a fine-tuned version of [Umong/wav2vec2-large-mms-1b-bengali](https://huggingface.co/Umong/wav2vec2-large-mms-1b-bengali) on an unknown dataset.
-It achieves the following results on the evaluation set:
-- eval_loss: 1.3414
-- eval_wer: 0.6114
-- eval_runtime: 393.3932
-- eval_samples_per_second: 2.542
-- eval_steps_per_second: 1.271
-- epoch: 0.01
-- step: 40
-
-## Model description
-
-More information needed
-
-## Intended uses & limitations
-
-More information needed
-
-## Training and evaluation data
-
-More information needed
-
 ## Training procedure
 
-### Training hyperparameters
-
-The following hyperparameters were used during training:
-- learning_rate: 2e-05
-- train_batch_size: 8
-- eval_batch_size: 2
-- seed: 42
-- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
-- lr_scheduler_type: cosine
-- lr_scheduler_warmup_steps: 600
-- training_steps: 100
-
 ### Framework versions
 
-- Transformers 4.33.0
-- Pytorch 2.0.0
-- Datasets 2.1.0
-- Tokenizers 0.13.3
+
+- PEFT 0.5.0

adapter_config.json

@@ -0,0 +1,24 @@
+{
+  "auto_mapping": {
+    "base_model_class": "Wav2Vec2ForCTC",
+    "parent_library": "transformers.models.wav2vec2.modeling_wav2vec2"
+  },
+  "base_model_name_or_path": "Umong/wav2vec2-large-mms-1b-bengali",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 64,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": null
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:927a83bb20374c5a09705fc3445f9ac6a684926cdb530ce0adee4de4fdfaa186
+size 31528333