skit-ai
/

speechllm-2B

Feature Extraction

speech-language

Model card Files Files and versions Community

shangeth commited on Jun 18

Commit

7eacacf

•

1 Parent(s): 64a7de7

Upload model

Files changed (2) hide show

README.md +44 -45
config.json +1 -6

README.md CHANGED Viewed

@@ -1,58 +1,57 @@
 ---
 license: apache-2.0
 datasets:
 - mozilla-foundation/common_voice_16_1
 - openslr/librispeech_asr
-language:
-- en
 metrics:
 - wer
-library_name: transformers
 model-index:
 - name: SpeechLLM
   results:
-      - task:
-          name: Automatic Speech Recognition
-          type: automatic-speech-recognition
-        dataset:
-          name: LibriSpeech (clean)
-          type: librispeech_asr
-          config: clean
-          split: test
-          args:
-            language: en
-        metrics:
-          - name: Test WER
-            type: wer
-            value: 12.3
-      - task:
-          name: Automatic Speech Recognition
-          type: automatic-speech-recognition
-        dataset:
-          name: LibriSpeech (other)
-          type: librispeech_asr
-          config: other
-          split: test
-          args:
-            language: en
-        metrics:
-          - name: Test WER
-            type: wer
-            value: 18.9
-      - task:
-          name: Automatic Speech Recognition
-          type: automatic-speech-recognition
-        dataset:
-          name: Common Voice 16.1
-          type: common_voice_16_1
-          split: test
-          args:
-            language: en
-        metrics:
-          - name: Test WER
-            type: wer
-            value: 25.01
 ---
 # SpeechLLM

 ---
+language:
+- en
 license: apache-2.0
+library_name: transformers
 datasets:
 - mozilla-foundation/common_voice_16_1
 - openslr/librispeech_asr
 metrics:
 - wer
 model-index:
 - name: SpeechLLM
   results:
+  - task:
+      type: automatic-speech-recognition
+      name: Automatic Speech Recognition
+    dataset:
+      name: LibriSpeech (clean)
+      type: librispeech_asr
+      config: clean
+      split: test
+      args:
+        language: en
+    metrics:
+    - type: wer
+      value: 12.3
+      name: Test WER
+  - task:
+      type: automatic-speech-recognition
+      name: Automatic Speech Recognition
+    dataset:
+      name: LibriSpeech (other)
+      type: librispeech_asr
+      config: other
+      split: test
+      args:
+        language: en
+    metrics:
+    - type: wer
+      value: 18.9
+      name: Test WER
+  - task:
+      type: automatic-speech-recognition
+      name: Automatic Speech Recognition
+    dataset:
+      name: Common Voice 16.1
+      type: common_voice_16_1
+      split: test
+      args:
+        language: en
+    metrics:
+    - type: wer
+      value: 25.01
+      name: Test WER
 ---
 # SpeechLLM

config.json CHANGED Viewed

@@ -1,14 +1,9 @@
 {
-  "architectures": [
-    "SpeechLLMModel"
-  ],
   "audio_enc_dim": 1280,
   "auto_map": {
-    "AutoConfig": "config.SpeechLLMModelConfig",
-    "AutoModel": "model.SpeechLLMModel"
   },
   "llm_dim": 2048,
   "model_type": "custom_model",
-  "torch_dtype": "float32",
   "transformers_version": "4.38.2"
 }

 {
   "audio_enc_dim": 1280,
   "auto_map": {
+    "AutoConfig": "config.SpeechLLMModelConfig"
   },
   "llm_dim": 2048,
   "model_type": "custom_model",
   "transformers_version": "4.38.2"
 }