Link Gemini audio listening atlas and annotation dataset
Browse files
README.md
CHANGED
|
@@ -41,6 +41,8 @@ prepare annotations; captions were not model inputs or an autoregressive trainin
|
|
| 41 |
CPS is a scalar prediction rather than a transcript. The requested separate MOSS caption
|
| 42 |
LoRAs are outside this release and were not trained as part of these two runs.
|
| 43 |
|
|
|
|
|
|
|
| 44 |
## Results and related releases
|
| 45 |
|
| 46 |
- **[Comprehensive English benchmark report](https://laion-whisper-base-small-emotion-voice-burst.static.hf.space/benchmark.html)**:
|
|
|
|
| 41 |
CPS is a scalar prediction rather than a transcript. The requested separate MOSS caption
|
| 42 |
LoRAs are outside this release and were not trained as part of these two runs.
|
| 43 |
|
| 44 |
+
**[Explore 1,000 real-audio examples in the new listening atlas](https://laion-whisper-gemini-audio-atlas.static.hf.space/)**: 50 timed vocal bursts, 20-query Orange timbre and identity neighbor pages, 40 EmoNet and 57 VoiceNet top-ten rankings, and five-tier quality pages. [Download the Gemini annotation dataset](https://huggingface.co/datasets/laion/whisper-gemini-voice-annotations).
|
| 45 |
+
|
| 46 |
## Results and related releases
|
| 47 |
|
| 48 |
- **[Comprehensive English benchmark report](https://laion-whisper-base-small-emotion-voice-burst.static.hf.space/benchmark.html)**:
|