Add Samples section: 5 playable clips with reference text and Dynamic ASR output

README.md

@@ -100,6 +100,60 @@ Any wav is mixed to mono and resampled to 16 kHz; clips over ~20 s are cut at qu
 
 Pocket shares the limitations listed below, with higher error than the 1B models.
 
+## Samples
+
+Hear the input and read what the model wrote. The input clips are **synthetic speech** from our [Dynamic Accent](https://huggingface.co/Modularcomputing/dynamic-accent-pro-v1.1) Flash-DPO TTS (female `waxal_ibo_5` or male anchor voice), not real recordings, so they are cleaner than real-world audio. The transcripts come from an internal Dynamic ASR checkpoint newer than `real/` (it adds a Yoruba tone-mark fix and is not one of the files in this repository yet): **with LM** = decoding with a 4-gram KenLM, as the [Duplex](https://huggingface.co/Modularcomputing/dynamic-accent-duplex) agent uses on final segments; **greedy** = plain CTC, no LM. Output is lower-case with no punctuation, and Igbo has no tone marks by design. Audio: mono MP3, CC-BY-SA-4.0.
+
+**1. Igbo** (female TTS voice)
+
+<audio controls src="https://huggingface.co/Modularcomputing/dynamic-asr/resolve/main/samples/tts_01_igbo_female_waxal_ibo5.mp3"></audio>
+
+| | text |
+|---|---|
+| reference | Ndewo, kedụ ka ị mere? Anyị ga-aga ahịa echi n'ụtụtụ. |
+| Dynamic ASR, with LM | nde wo kedu ka i mere anyị ga agaghi echi n'ụtụtụ |
+| Dynamic ASR, greedy | ndewo kedu ka ị mere anyị ga aga ahị echi n'ụtụtụ |
+
+**2. Yoruba** (female TTS voice)
+
+<audio controls src="https://huggingface.co/Modularcomputing/dynamic-asr/resolve/main/samples/tts_02_yoruba_tones_female_waxal_ibo5.mp3"></audio>
+
+| | text |
+|---|---|
+| reference | Ẹ káàárọ̀! Ṣé dáadáa ni ẹ wà? Mo fẹ́ lọ sí ọjà lọ́la. |
+| Dynamic ASR, with LM | ẹkáàárọ̀ ṣé dáadáa ni ẹwà mo fẹ́ lọ sí ọjà lọ́lá |
+| Dynamic ASR, greedy | ẹká àrọ̀ ṣé dáadá ni ẹwà mo fẹ́ lọ sí ọjà lọla |
+
+**3. Hausa** (male TTS voice)
+
+<audio controls src="https://huggingface.co/Modularcomputing/dynamic-asr/resolve/main/samples/tts_03_hausa_flash_default_male.mp3"></audio>
+
+| | text |
+|---|---|
+| reference | Sannu da zuwa. Yaya aiki? Zan tafi Kano gobe da safe. |
+| Dynamic ASR, with LM | sannu da zuwa yaya aiki zan tafi kano gobe a safe |
+| Dynamic ASR, greedy | sanuda zuwa yaya aiki zan tafi kano gube da safe |
+
+**4. Pidgin** (female TTS voice)
+
+<audio controls src="https://huggingface.co/Modularcomputing/dynamic-asr/resolve/main/samples/tts_04_pidgin_female_waxal_ibo5.mp3"></audio>
+
+| | text |
+|---|---|
+| reference | How far, my guy? Abeg make we see for evening, I dey come. |
+| Dynamic ASR, with LM | how far my guy abeg make we see for evenin i dey come |
+| Dynamic ASR, greedy | how far my guy abeg make we see for evening i dey come |
+
+**5. Igbo + English (code-switch)** (male TTS voice)
+
+<audio controls src="https://huggingface.co/Modularcomputing/dynamic-asr/resolve/main/samples/tts_06_cs_igbo_english_flash_default_male.mp3"></audio>
+
+| | text |
+|---|---|
+| reference | Biko, can you send me the report before Friday? Daalụ. |
+| Dynamic ASR, with LM | biko can you send me the report before friday talo |
+| Dynamic ASR, greedy | biko can you send me the report before friday daalo |
+
 ## Results
 
 All test data is held out (never trained on). Scores are WER / CER after lower-casing and stripping punctuation; "no-diacritic" CER folds tone marks and dots. Decoding: greedy CTC with a Latin-script logit mask (the duplex setting).