openbmb
/

MiniCPM-o-2_6

Model card Files Files and versions Community

bokesyo commited on 18 days ago

Commit

e1b08c1

verified ·

1 Parent(s): ca9a10b

Update README.md

Browse files

Files changed (1) hide show

README.md +11 -5

README.md CHANGED Viewed

@@ -1149,6 +1149,8 @@ model.tts.float()
 </details>
 ##### Mimick
 `Mimick` task reflects a model's end-to-end speech modeling capability. The model takes audio input, and outputs an ASR transcription and subsequently reconstructs the original audio with high similarity. The higher the similarity between the reconstructed audio and the original audio, the stronger the model's foundational capability in end-to-end speech modeling.
@@ -1173,6 +1175,8 @@ res = model.chat(
 </details>
 ##### General Speech Conversation with Configurable Voices
 A general usage scenario of MiniCPM-o 2.6 is role-playing a specific character based on the audio prompt. It will mimic the voice of the character to some extent and act like the character in text, including language style. In this mode, MiniCPM-o-2.6 will sounds **more natural and human-like**. Self-defined audio prompts can be used to customize the voice of the character in an end-to-end manner.
@@ -1216,6 +1220,8 @@ print(res)
 </details>
 ##### Speech Conversation as an AI Assistant
 An enhanced feature of MiniCPM-o-2.6 is to act as an AI assistant, but only with limited choice of voices. In this mode, MiniCPM-o-2.6 is **less human-like and more like a voice assistant**. But it is more instruction-following.
@@ -1257,6 +1263,7 @@ print(res)
 ```
 </details>
 ##### Instruction-to-Speech
@@ -1285,6 +1292,8 @@ res = model.chat(
 ```
 </details>
 ##### Voice Cloning
 MiniCPM-o-2.6 can also do zero-shot text-to-speech, aka **Voice Cloning**. With this mode, model will act like a TTS model.
@@ -1312,6 +1321,8 @@ res = model.chat(
 ```
 </details>
 ##### Addressing Various Audio Understanding Tasks
 MiniCPM-o-2.6 can also be used to address various audio understanding tasks, such as ASR, speaker analysis, general audio captioning, and sound scene tagging.
@@ -1349,11 +1360,6 @@ print(res)
-</details>
 ### Vision-Only mode
 `MiniCPM-o-2_6` has the same inference methods as `MiniCPM-V-2_6`

 </details>
+<br/>
 ##### Mimick
 `Mimick` task reflects a model's end-to-end speech modeling capability. The model takes audio input, and outputs an ASR transcription and subsequently reconstructs the original audio with high similarity. The higher the similarity between the reconstructed audio and the original audio, the stronger the model's foundational capability in end-to-end speech modeling.
 </details>
+<br/>
 ##### General Speech Conversation with Configurable Voices
 A general usage scenario of MiniCPM-o 2.6 is role-playing a specific character based on the audio prompt. It will mimic the voice of the character to some extent and act like the character in text, including language style. In this mode, MiniCPM-o-2.6 will sounds **more natural and human-like**. Self-defined audio prompts can be used to customize the voice of the character in an end-to-end manner.
 </details>
+<br/>
 ##### Speech Conversation as an AI Assistant
 An enhanced feature of MiniCPM-o-2.6 is to act as an AI assistant, but only with limited choice of voices. In this mode, MiniCPM-o-2.6 is **less human-like and more like a voice assistant**. But it is more instruction-following.
 ```
 </details>
+<br/>
 ##### Instruction-to-Speech
 ```
 </details>
+<br/>
 ##### Voice Cloning
 MiniCPM-o-2.6 can also do zero-shot text-to-speech, aka **Voice Cloning**. With this mode, model will act like a TTS model.
 ```
 </details>
+<br/>
 ##### Addressing Various Audio Understanding Tasks
 MiniCPM-o-2.6 can also be used to address various audio understanding tasks, such as ASR, speaker analysis, general audio captioning, and sound scene tagging.
 ### Vision-Only mode
 `MiniCPM-o-2_6` has the same inference methods as `MiniCPM-V-2_6`